{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "YdQPrKjkMhlp" }, "outputs": [], "source": [ "ALGO = \"dqn\"\n", "ENV = \"SpaceInvadersNoFrameskip-v4\"\n", "IS_EVAL_DETERMINISTIC = True\n", "MODEL_NAME = f\"{ALGO}-sb3-{ENV}\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "RgQFeu858QEi" }, "outputs": [], "source": [ "%%capture\n", "!apt install python-opengl\n", "!apt install ffmpeg\n", "!apt install xvfb\n", "!apt install swig\n", "!apt-get install swig cmake freeglut3-dev" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "BcMKMQiV8uqv" }, "outputs": [], "source": [ "%%capture\n", "!pip install stable-baselines3[extra] box2d huggingface_sb3 pyglet==1.5.1 pyvirtualdisplay==3.0" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "pnSOaJfd8oCh" }, "outputs": [], "source": [ "%%capture\n", "from pyvirtualdisplay import Display\n", "\n", "virtual_display = Display(visible=0, size=(1400, 900))\n", "virtual_display.start()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "wF3U_U5JM_JP", "outputId": "9b591dd9-72e5-477f-9151-51b3574fb7b2" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", " _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n", " _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", " _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n", " _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", " _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n", " \n", " To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n", "Token: \n", "Add token as git credential? (Y/n) \n", "Token is valid.\n", "Your token has been saved in your configured git credential helpers (store).\n", "Your token has been saved to /root/.cache/huggingface/token\n", "Login successful\n" ] } ], "source": [ "!git config --global credential.helper store\n", "!huggingface-cli login" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "aENGEenlE5A3", "outputId": "cdecc60c-862d-48d4-ab18-204e0e5d301b" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1;30;43mStreaming output truncated to the last 5000 lines.\u001b[0m\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00559 |\n", "| n_updates | 293223 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.58e+03 |\n", "| ep_rew_mean | 550 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39960 |\n", "| fps | 710 |\n", "| time_elapsed | 13491 |\n", "| total_timesteps | 9584512 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0384 |\n", "| n_updates | 293265 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.58e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39964 |\n", "| fps | 710 |\n", "| time_elapsed | 13493 |\n", "| total_timesteps | 9585952 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0247 |\n", "| n_updates | 293310 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.6e+03 |\n", "| ep_rew_mean | 557 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39968 |\n", "| fps | 710 |\n", "| time_elapsed | 13497 |\n", "| total_timesteps | 9588440 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0276 |\n", "| n_updates | 293388 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.6e+03 |\n", "| ep_rew_mean | 557 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39972 |\n", "| fps | 710 |\n", "| time_elapsed | 13498 |\n", "| total_timesteps | 9589496 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00934 |\n", "| n_updates | 293421 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.59e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39976 |\n", "| fps | 710 |\n", "| time_elapsed | 13500 |\n", "| total_timesteps | 9590760 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0709 |\n", "| n_updates | 293461 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 554 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39980 |\n", "| fps | 710 |\n", "| time_elapsed | 13501 |\n", "| total_timesteps | 9591464 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0103 |\n", "| n_updates | 293483 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.55e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39984 |\n", "| fps | 710 |\n", "| time_elapsed | 13502 |\n", "| total_timesteps | 9592776 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00816 |\n", "| n_updates | 293524 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.55e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39988 |\n", "| fps | 710 |\n", "| time_elapsed | 13503 |\n", "| total_timesteps | 9593536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0543 |\n", "| n_updates | 293547 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39992 |\n", "| fps | 710 |\n", "| time_elapsed | 13505 |\n", "| total_timesteps | 9594496 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00431 |\n", "| n_updates | 293577 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 547 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 39996 |\n", "| fps | 710 |\n", "| time_elapsed | 13507 |\n", "| total_timesteps | 9596000 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00963 |\n", "| n_updates | 293624 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 547 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40000 |\n", "| fps | 710 |\n", "| time_elapsed | 13508 |\n", "| total_timesteps | 9597216 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0125 |\n", "| n_updates | 293662 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40004 |\n", "| fps | 710 |\n", "| time_elapsed | 13510 |\n", "| total_timesteps | 9598552 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00645 |\n", "| n_updates | 293704 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40008 |\n", "| fps | 710 |\n", "| time_elapsed | 13512 |\n", "| total_timesteps | 9600088 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00603 |\n", "| n_updates | 293752 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40012 |\n", "| fps | 710 |\n", "| time_elapsed | 13513 |\n", "| total_timesteps | 9600896 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00729 |\n", "| n_updates | 293777 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40016 |\n", "| fps | 710 |\n", "| time_elapsed | 13515 |\n", "| total_timesteps | 9602128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0898 |\n", "| n_updates | 293816 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.55e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40020 |\n", "| fps | 710 |\n", "| time_elapsed | 13517 |\n", "| total_timesteps | 9603496 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0314 |\n", "| n_updates | 293859 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40024 |\n", "| fps | 710 |\n", "| time_elapsed | 13518 |\n", "| total_timesteps | 9604432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0199 |\n", "| n_updates | 293888 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40028 |\n", "| fps | 710 |\n", "| time_elapsed | 13520 |\n", "| total_timesteps | 9605520 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0124 |\n", "| n_updates | 293922 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 547 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40032 |\n", "| fps | 710 |\n", "| time_elapsed | 13521 |\n", "| total_timesteps | 9606768 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00663 |\n", "| n_updates | 293961 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40036 |\n", "| fps | 710 |\n", "| time_elapsed | 13522 |\n", "| total_timesteps | 9607560 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0202 |\n", "| n_updates | 293986 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40040 |\n", "| fps | 710 |\n", "| time_elapsed | 13524 |\n", "| total_timesteps | 9608952 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0146 |\n", "| n_updates | 294029 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 551 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40044 |\n", "| fps | 710 |\n", "| time_elapsed | 13527 |\n", "| total_timesteps | 9610816 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00771 |\n", "| n_updates | 294087 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40048 |\n", "| fps | 710 |\n", "| time_elapsed | 13529 |\n", "| total_timesteps | 9612176 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00975 |\n", "| n_updates | 294130 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40052 |\n", "| fps | 710 |\n", "| time_elapsed | 13531 |\n", "| total_timesteps | 9613472 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0233 |\n", "| n_updates | 294170 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40056 |\n", "| fps | 710 |\n", "| time_elapsed | 13532 |\n", "| total_timesteps | 9614432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0104 |\n", "| n_updates | 294200 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40060 |\n", "| fps | 710 |\n", "| time_elapsed | 13533 |\n", "| total_timesteps | 9615584 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0607 |\n", "| n_updates | 294236 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 552 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40064 |\n", "| fps | 710 |\n", "| time_elapsed | 13536 |\n", "| total_timesteps | 9617120 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00958 |\n", "| n_updates | 294284 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 551 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40068 |\n", "| fps | 710 |\n", "| time_elapsed | 13537 |\n", "| total_timesteps | 9618264 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0103 |\n", "| n_updates | 294320 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.55e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40072 |\n", "| fps | 710 |\n", "| time_elapsed | 13538 |\n", "| total_timesteps | 9619016 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00857 |\n", "| n_updates | 294344 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.55e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40076 |\n", "| fps | 710 |\n", "| time_elapsed | 13541 |\n", "| total_timesteps | 9620792 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0196 |\n", "| n_updates | 294399 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 558 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40080 |\n", "| fps | 710 |\n", "| time_elapsed | 13542 |\n", "| total_timesteps | 9621552 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.019 |\n", "| n_updates | 294423 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 557 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40084 |\n", "| fps | 710 |\n", "| time_elapsed | 13543 |\n", "| total_timesteps | 9622728 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00725 |\n", "| n_updates | 294460 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 552 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40088 |\n", "| fps | 710 |\n", "| time_elapsed | 13545 |\n", "| total_timesteps | 9624096 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0425 |\n", "| n_updates | 294502 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 552 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40092 |\n", "| fps | 710 |\n", "| time_elapsed | 13546 |\n", "| total_timesteps | 9624736 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0139 |\n", "| n_updates | 294522 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40096 |\n", "| fps | 710 |\n", "| time_elapsed | 13549 |\n", "| total_timesteps | 9627000 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0201 |\n", "| n_updates | 294593 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40100 |\n", "| fps | 710 |\n", "| time_elapsed | 13551 |\n", "| total_timesteps | 9628760 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00768 |\n", "| n_updates | 294648 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40104 |\n", "| fps | 710 |\n", "| time_elapsed | 13553 |\n", "| total_timesteps | 9629624 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0194 |\n", "| n_updates | 294675 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40108 |\n", "| fps | 710 |\n", "| time_elapsed | 13554 |\n", "| total_timesteps | 9630344 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0149 |\n", "| n_updates | 294698 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 539 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40112 |\n", "| fps | 710 |\n", "| time_elapsed | 13554 |\n", "| total_timesteps | 9630872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0113 |\n", "| n_updates | 294714 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 535 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40116 |\n", "| fps | 710 |\n", "| time_elapsed | 13556 |\n", "| total_timesteps | 9632072 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00624 |\n", "| n_updates | 294752 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 535 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40120 |\n", "| fps | 710 |\n", "| time_elapsed | 13558 |\n", "| total_timesteps | 9633896 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00755 |\n", "| n_updates | 294809 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 535 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40124 |\n", "| fps | 710 |\n", "| time_elapsed | 13560 |\n", "| total_timesteps | 9635440 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00812 |\n", "| n_updates | 294857 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 535 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40128 |\n", "| fps | 710 |\n", "| time_elapsed | 13562 |\n", "| total_timesteps | 9636552 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0261 |\n", "| n_updates | 294892 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.34e+03 |\n", "| ep_rew_mean | 529 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40132 |\n", "| fps | 710 |\n", "| time_elapsed | 13564 |\n", "| total_timesteps | 9638160 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0047 |\n", "| n_updates | 294942 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.35e+03 |\n", "| ep_rew_mean | 527 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40136 |\n", "| fps | 710 |\n", "| time_elapsed | 13565 |\n", "| total_timesteps | 9638912 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0262 |\n", "| n_updates | 294965 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.36e+03 |\n", "| ep_rew_mean | 528 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40140 |\n", "| fps | 710 |\n", "| time_elapsed | 13568 |\n", "| total_timesteps | 9640664 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0141 |\n", "| n_updates | 295020 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.36e+03 |\n", "| ep_rew_mean | 528 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40144 |\n", "| fps | 710 |\n", "| time_elapsed | 13570 |\n", "| total_timesteps | 9642512 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0314 |\n", "| n_updates | 295078 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.36e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40148 |\n", "| fps | 710 |\n", "| time_elapsed | 13572 |\n", "| total_timesteps | 9643656 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0102 |\n", "| n_updates | 295114 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.37e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40152 |\n", "| fps | 710 |\n", "| time_elapsed | 13573 |\n", "| total_timesteps | 9644720 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00462 |\n", "| n_updates | 295147 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40156 |\n", "| fps | 710 |\n", "| time_elapsed | 13574 |\n", "| total_timesteps | 9645624 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00585 |\n", "| n_updates | 295175 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 531 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40160 |\n", "| fps | 710 |\n", "| time_elapsed | 13577 |\n", "| total_timesteps | 9647768 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0175 |\n", "| n_updates | 295242 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.38e+03 |\n", "| ep_rew_mean | 525 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40164 |\n", "| fps | 710 |\n", "| time_elapsed | 13579 |\n", "| total_timesteps | 9648936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0714 |\n", "| n_updates | 295279 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.38e+03 |\n", "| ep_rew_mean | 526 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40168 |\n", "| fps | 710 |\n", "| time_elapsed | 13580 |\n", "| total_timesteps | 9649736 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.026 |\n", "| n_updates | 295304 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.37e+03 |\n", "| ep_rew_mean | 523 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40172 |\n", "| fps | 710 |\n", "| time_elapsed | 13582 |\n", "| total_timesteps | 9650840 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0228 |\n", "| n_updates | 295338 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 524 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40176 |\n", "| fps | 710 |\n", "| time_elapsed | 13584 |\n", "| total_timesteps | 9652480 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0451 |\n", "| n_updates | 295389 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 525 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40180 |\n", "| fps | 710 |\n", "| time_elapsed | 13584 |\n", "| total_timesteps | 9652872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0193 |\n", "| n_updates | 295402 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40184 |\n", "| fps | 710 |\n", "| time_elapsed | 13586 |\n", "| total_timesteps | 9653944 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0103 |\n", "| n_updates | 295435 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40188 |\n", "| fps | 710 |\n", "| time_elapsed | 13588 |\n", "| total_timesteps | 9655400 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0136 |\n", "| n_updates | 295481 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 531 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40192 |\n", "| fps | 710 |\n", "| time_elapsed | 13589 |\n", "| total_timesteps | 9656336 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00641 |\n", "| n_updates | 295510 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 534 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40196 |\n", "| fps | 710 |\n", "| time_elapsed | 13590 |\n", "| total_timesteps | 9657064 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0153 |\n", "| n_updates | 295533 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 533 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40200 |\n", "| fps | 710 |\n", "| time_elapsed | 13591 |\n", "| total_timesteps | 9657768 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00907 |\n", "| n_updates | 295555 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 528 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40204 |\n", "| fps | 710 |\n", "| time_elapsed | 13592 |\n", "| total_timesteps | 9658536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0102 |\n", "| n_updates | 295579 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.38e+03 |\n", "| ep_rew_mean | 526 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40208 |\n", "| fps | 710 |\n", "| time_elapsed | 13594 |\n", "| total_timesteps | 9659856 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0121 |\n", "| n_updates | 295620 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 526 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40212 |\n", "| fps | 710 |\n", "| time_elapsed | 13596 |\n", "| total_timesteps | 9661456 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.056 |\n", "| n_updates | 295670 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.36e+03 |\n", "| ep_rew_mean | 523 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40216 |\n", "| fps | 710 |\n", "| time_elapsed | 13597 |\n", "| total_timesteps | 9661952 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0117 |\n", "| n_updates | 295685 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.35e+03 |\n", "| ep_rew_mean | 522 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40220 |\n", "| fps | 710 |\n", "| time_elapsed | 13599 |\n", "| total_timesteps | 9663360 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0115 |\n", "| n_updates | 295729 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.33e+03 |\n", "| ep_rew_mean | 517 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40224 |\n", "| fps | 710 |\n", "| time_elapsed | 13600 |\n", "| total_timesteps | 9664400 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00686 |\n", "| n_updates | 295762 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.34e+03 |\n", "| ep_rew_mean | 516 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40228 |\n", "| fps | 710 |\n", "| time_elapsed | 13601 |\n", "| total_timesteps | 9665064 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0192 |\n", "| n_updates | 295783 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.33e+03 |\n", "| ep_rew_mean | 516 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40232 |\n", "| fps | 710 |\n", "| time_elapsed | 13603 |\n", "| total_timesteps | 9666464 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0291 |\n", "| n_updates | 295826 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 513 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40236 |\n", "| fps | 710 |\n", "| time_elapsed | 13604 |\n", "| total_timesteps | 9667480 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0423 |\n", "| n_updates | 295858 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.32e+03 |\n", "| ep_rew_mean | 511 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40240 |\n", "| fps | 710 |\n", "| time_elapsed | 13606 |\n", "| total_timesteps | 9668616 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0529 |\n", "| n_updates | 295894 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 508 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40244 |\n", "| fps | 710 |\n", "| time_elapsed | 13608 |\n", "| total_timesteps | 9670288 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0866 |\n", "| n_updates | 295946 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.3e+03 |\n", "| ep_rew_mean | 503 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40248 |\n", "| fps | 710 |\n", "| time_elapsed | 13610 |\n", "| total_timesteps | 9671536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0188 |\n", "| n_updates | 295985 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.3e+03 |\n", "| ep_rew_mean | 504 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40252 |\n", "| fps | 710 |\n", "| time_elapsed | 13611 |\n", "| total_timesteps | 9672024 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0282 |\n", "| n_updates | 296000 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.3e+03 |\n", "| ep_rew_mean | 504 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40256 |\n", "| fps | 710 |\n", "| time_elapsed | 13613 |\n", "| total_timesteps | 9674072 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.025 |\n", "| n_updates | 296064 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.3e+03 |\n", "| ep_rew_mean | 504 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40260 |\n", "| fps | 710 |\n", "| time_elapsed | 13614 |\n", "| total_timesteps | 9674664 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0903 |\n", "| n_updates | 296083 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.32e+03 |\n", "| ep_rew_mean | 502 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40264 |\n", "| fps | 710 |\n", "| time_elapsed | 13616 |\n", "| total_timesteps | 9676040 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0857 |\n", "| n_updates | 296126 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 499 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40268 |\n", "| fps | 710 |\n", "| time_elapsed | 13617 |\n", "| total_timesteps | 9676536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0507 |\n", "| n_updates | 296141 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 498 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40272 |\n", "| fps | 710 |\n", "| time_elapsed | 13618 |\n", "| total_timesteps | 9677792 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0136 |\n", "| n_updates | 296180 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 497 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40276 |\n", "| fps | 710 |\n", "| time_elapsed | 13620 |\n", "| total_timesteps | 9679136 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0211 |\n", "| n_updates | 296222 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.32e+03 |\n", "| ep_rew_mean | 497 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40280 |\n", "| fps | 710 |\n", "| time_elapsed | 13623 |\n", "| total_timesteps | 9681000 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0189 |\n", "| n_updates | 296281 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 493 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40284 |\n", "| fps | 710 |\n", "| time_elapsed | 13624 |\n", "| total_timesteps | 9681888 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0292 |\n", "| n_updates | 296308 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 494 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40288 |\n", "| fps | 710 |\n", "| time_elapsed | 13625 |\n", "| total_timesteps | 9682672 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0116 |\n", "| n_updates | 296333 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 488 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40292 |\n", "| fps | 710 |\n", "| time_elapsed | 13626 |\n", "| total_timesteps | 9683304 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0118 |\n", "| n_updates | 296353 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27e+03 |\n", "| ep_rew_mean | 486 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40296 |\n", "| fps | 710 |\n", "| time_elapsed | 13627 |\n", "| total_timesteps | 9684016 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00861 |\n", "| n_updates | 296375 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27e+03 |\n", "| ep_rew_mean | 488 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40300 |\n", "| fps | 710 |\n", "| time_elapsed | 13628 |\n", "| total_timesteps | 9684720 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.009 |\n", "| n_updates | 296397 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 488 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40304 |\n", "| fps | 710 |\n", "| time_elapsed | 13630 |\n", "| total_timesteps | 9686304 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0261 |\n", "| n_updates | 296446 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 488 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40308 |\n", "| fps | 710 |\n", "| time_elapsed | 13632 |\n", "| total_timesteps | 9687432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00495 |\n", "| n_updates | 296482 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 485 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40312 |\n", "| fps | 710 |\n", "| time_elapsed | 13633 |\n", "| total_timesteps | 9688664 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0229 |\n", "| n_updates | 296520 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 485 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40316 |\n", "| fps | 710 |\n", "| time_elapsed | 13635 |\n", "| total_timesteps | 9689648 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0215 |\n", "| n_updates | 296551 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 485 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40320 |\n", "| fps | 710 |\n", "| time_elapsed | 13636 |\n", "| total_timesteps | 9690440 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0166 |\n", "| n_updates | 296576 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 482 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40324 |\n", "| fps | 710 |\n", "| time_elapsed | 13638 |\n", "| total_timesteps | 9691808 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0308 |\n", "| n_updates | 296618 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 484 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40328 |\n", "| fps | 710 |\n", "| time_elapsed | 13639 |\n", "| total_timesteps | 9692624 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00627 |\n", "| n_updates | 296644 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 482 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40332 |\n", "| fps | 710 |\n", "| time_elapsed | 13641 |\n", "| total_timesteps | 9693952 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0244 |\n", "| n_updates | 296685 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 483 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40336 |\n", "| fps | 710 |\n", "| time_elapsed | 13642 |\n", "| total_timesteps | 9694632 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00614 |\n", "| n_updates | 296707 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 477 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40340 |\n", "| fps | 710 |\n", "| time_elapsed | 13643 |\n", "| total_timesteps | 9695784 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.035 |\n", "| n_updates | 296743 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 476 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40344 |\n", "| fps | 710 |\n", "| time_elapsed | 13645 |\n", "| total_timesteps | 9697192 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0216 |\n", "| n_updates | 296787 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 477 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40348 |\n", "| fps | 710 |\n", "| time_elapsed | 13648 |\n", "| total_timesteps | 9699312 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0117 |\n", "| n_updates | 296853 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 477 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40352 |\n", "| fps | 710 |\n", "| time_elapsed | 13650 |\n", "| total_timesteps | 9700728 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00541 |\n", "| n_updates | 296897 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 475 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40356 |\n", "| fps | 710 |\n", "| time_elapsed | 13651 |\n", "| total_timesteps | 9701696 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0186 |\n", "| n_updates | 296927 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 475 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40360 |\n", "| fps | 710 |\n", "| time_elapsed | 13652 |\n", "| total_timesteps | 9702344 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00499 |\n", "| n_updates | 296948 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.19e+03 |\n", "| ep_rew_mean | 471 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40364 |\n", "| fps | 710 |\n", "| time_elapsed | 13653 |\n", "| total_timesteps | 9703120 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0173 |\n", "| n_updates | 296972 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.19e+03 |\n", "| ep_rew_mean | 472 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40368 |\n", "| fps | 710 |\n", "| time_elapsed | 13655 |\n", "| total_timesteps | 9704512 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.015 |\n", "| n_updates | 297015 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 471 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40372 |\n", "| fps | 710 |\n", "| time_elapsed | 13657 |\n", "| total_timesteps | 9705880 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00877 |\n", "| n_updates | 297058 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 477 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40376 |\n", "| fps | 710 |\n", "| time_elapsed | 13658 |\n", "| total_timesteps | 9706984 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0494 |\n", "| n_updates | 297093 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.24e+03 |\n", "| ep_rew_mean | 480 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40380 |\n", "| fps | 710 |\n", "| time_elapsed | 13660 |\n", "| total_timesteps | 9708128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0182 |\n", "| n_updates | 297128 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40384 |\n", "| fps | 710 |\n", "| time_elapsed | 13662 |\n", "| total_timesteps | 9709800 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0162 |\n", "| n_updates | 297181 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 484 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40388 |\n", "| fps | 710 |\n", "| time_elapsed | 13663 |\n", "| total_timesteps | 9710592 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0394 |\n", "| n_updates | 297205 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 485 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40392 |\n", "| fps | 710 |\n", "| time_elapsed | 13664 |\n", "| total_timesteps | 9711520 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0378 |\n", "| n_updates | 297234 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 486 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40396 |\n", "| fps | 710 |\n", "| time_elapsed | 13665 |\n", "| total_timesteps | 9712088 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0321 |\n", "| n_updates | 297252 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.24e+03 |\n", "| ep_rew_mean | 481 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40400 |\n", "| fps | 710 |\n", "| time_elapsed | 13667 |\n", "| total_timesteps | 9713048 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0173 |\n", "| n_updates | 297282 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 480 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40404 |\n", "| fps | 710 |\n", "| time_elapsed | 13669 |\n", "| total_timesteps | 9714872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0111 |\n", "| n_updates | 297339 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 481 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40408 |\n", "| fps | 710 |\n", "| time_elapsed | 13671 |\n", "| total_timesteps | 9716432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0184 |\n", "| n_updates | 297388 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 480 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40412 |\n", "| fps | 710 |\n", "| time_elapsed | 13673 |\n", "| total_timesteps | 9717776 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00699 |\n", "| n_updates | 297430 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 477 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40416 |\n", "| fps | 710 |\n", "| time_elapsed | 13674 |\n", "| total_timesteps | 9718264 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0213 |\n", "| n_updates | 297445 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 476 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40420 |\n", "| fps | 710 |\n", "| time_elapsed | 13676 |\n", "| total_timesteps | 9719728 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.114 |\n", "| n_updates | 297491 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40424 |\n", "| fps | 710 |\n", "| time_elapsed | 13677 |\n", "| total_timesteps | 9720808 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0147 |\n", "| n_updates | 297525 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40428 |\n", "| fps | 710 |\n", "| time_elapsed | 13679 |\n", "| total_timesteps | 9721840 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00942 |\n", "| n_updates | 297557 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40432 |\n", "| fps | 710 |\n", "| time_elapsed | 13681 |\n", "| total_timesteps | 9723728 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00485 |\n", "| n_updates | 297616 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.19e+03 |\n", "| ep_rew_mean | 476 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40436 |\n", "| fps | 710 |\n", "| time_elapsed | 13682 |\n", "| total_timesteps | 9724440 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0183 |\n", "| n_updates | 297638 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.18e+03 |\n", "| ep_rew_mean | 473 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40440 |\n", "| fps | 710 |\n", "| time_elapsed | 13685 |\n", "| total_timesteps | 9726408 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0389 |\n", "| n_updates | 297700 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 479 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40444 |\n", "| fps | 710 |\n", "| time_elapsed | 13685 |\n", "| total_timesteps | 9726968 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0251 |\n", "| n_updates | 297717 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 480 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40448 |\n", "| fps | 710 |\n", "| time_elapsed | 13687 |\n", "| total_timesteps | 9728456 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0201 |\n", "| n_updates | 297764 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 483 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40452 |\n", "| fps | 710 |\n", "| time_elapsed | 13688 |\n", "| total_timesteps | 9728888 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0097 |\n", "| n_updates | 297777 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.2e+03 |\n", "| ep_rew_mean | 483 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40456 |\n", "| fps | 710 |\n", "| time_elapsed | 13690 |\n", "| total_timesteps | 9730184 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0156 |\n", "| n_updates | 297818 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.17e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40460 |\n", "| fps | 710 |\n", "| time_elapsed | 13691 |\n", "| total_timesteps | 9730872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0195 |\n", "| n_updates | 297839 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.18e+03 |\n", "| ep_rew_mean | 479 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40464 |\n", "| fps | 710 |\n", "| time_elapsed | 13692 |\n", "| total_timesteps | 9732040 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0169 |\n", "| n_updates | 297876 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.15e+03 |\n", "| ep_rew_mean | 476 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40468 |\n", "| fps | 710 |\n", "| time_elapsed | 13695 |\n", "| total_timesteps | 9734016 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.022 |\n", "| n_updates | 297937 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.16e+03 |\n", "| ep_rew_mean | 476 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40472 |\n", "| fps | 710 |\n", "| time_elapsed | 13697 |\n", "| total_timesteps | 9735352 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0524 |\n", "| n_updates | 297979 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.16e+03 |\n", "| ep_rew_mean | 475 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40476 |\n", "| fps | 710 |\n", "| time_elapsed | 13699 |\n", "| total_timesteps | 9736848 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.162 |\n", "| n_updates | 298026 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.18e+03 |\n", "| ep_rew_mean | 478 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40480 |\n", "| fps | 710 |\n", "| time_elapsed | 13700 |\n", "| total_timesteps | 9737616 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00947 |\n", "| n_updates | 298050 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 489 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40484 |\n", "| fps | 710 |\n", "| time_elapsed | 13701 |\n", "| total_timesteps | 9738368 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0125 |\n", "| n_updates | 298073 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.21e+03 |\n", "| ep_rew_mean | 487 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40488 |\n", "| fps | 710 |\n", "| time_elapsed | 13704 |\n", "| total_timesteps | 9740528 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0113 |\n", "| n_updates | 298141 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.22e+03 |\n", "| ep_rew_mean | 489 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40492 |\n", "| fps | 710 |\n", "| time_elapsed | 13707 |\n", "| total_timesteps | 9742888 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0309 |\n", "| n_updates | 298215 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.22e+03 |\n", "| ep_rew_mean | 492 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40496 |\n", "| fps | 710 |\n", "| time_elapsed | 13708 |\n", "| total_timesteps | 9743624 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0178 |\n", "| n_updates | 298238 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 494 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40500 |\n", "| fps | 710 |\n", "| time_elapsed | 13709 |\n", "| total_timesteps | 9744360 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.101 |\n", "| n_updates | 298261 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 494 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40504 |\n", "| fps | 710 |\n", "| time_elapsed | 13711 |\n", "| total_timesteps | 9745480 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0127 |\n", "| n_updates | 298296 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 494 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40508 |\n", "| fps | 710 |\n", "| time_elapsed | 13713 |\n", "| total_timesteps | 9747056 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0139 |\n", "| n_updates | 298345 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 499 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40512 |\n", "| fps | 710 |\n", "| time_elapsed | 13715 |\n", "| total_timesteps | 9748912 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0223 |\n", "| n_updates | 298403 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 499 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40516 |\n", "| fps | 710 |\n", "| time_elapsed | 13718 |\n", "| total_timesteps | 9750664 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0434 |\n", "| n_updates | 298458 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 503 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40520 |\n", "| fps | 710 |\n", "| time_elapsed | 13719 |\n", "| total_timesteps | 9751872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.069 |\n", "| n_updates | 298495 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 505 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40524 |\n", "| fps | 710 |\n", "| time_elapsed | 13721 |\n", "| total_timesteps | 9753304 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00795 |\n", "| n_updates | 298540 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 503 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40528 |\n", "| fps | 710 |\n", "| time_elapsed | 13722 |\n", "| total_timesteps | 9754216 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00892 |\n", "| n_updates | 298569 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 503 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40532 |\n", "| fps | 710 |\n", "| time_elapsed | 13724 |\n", "| total_timesteps | 9755352 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0515 |\n", "| n_updates | 298604 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 506 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40536 |\n", "| fps | 710 |\n", "| time_elapsed | 13724 |\n", "| total_timesteps | 9755592 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0251 |\n", "| n_updates | 298612 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 510 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40540 |\n", "| fps | 710 |\n", "| time_elapsed | 13725 |\n", "| total_timesteps | 9756416 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00797 |\n", "| n_updates | 298637 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.26e+03 |\n", "| ep_rew_mean | 513 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40544 |\n", "| fps | 710 |\n", "| time_elapsed | 13728 |\n", "| total_timesteps | 9758088 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0254 |\n", "| n_updates | 298690 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27e+03 |\n", "| ep_rew_mean | 517 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40548 |\n", "| fps | 710 |\n", "| time_elapsed | 13729 |\n", "| total_timesteps | 9759048 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0327 |\n", "| n_updates | 298720 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.23e+03 |\n", "| ep_rew_mean | 513 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40552 |\n", "| fps | 710 |\n", "| time_elapsed | 13730 |\n", "| total_timesteps | 9759520 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0114 |\n", "| n_updates | 298734 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.24e+03 |\n", "| ep_rew_mean | 515 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40556 |\n", "| fps | 710 |\n", "| time_elapsed | 13732 |\n", "| total_timesteps | 9761432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0314 |\n", "| n_updates | 298794 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.24e+03 |\n", "| ep_rew_mean | 514 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40560 |\n", "| fps | 710 |\n", "| time_elapsed | 13734 |\n", "| total_timesteps | 9762688 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0361 |\n", "| n_updates | 298833 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.25e+03 |\n", "| ep_rew_mean | 518 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40564 |\n", "| fps | 710 |\n", "| time_elapsed | 13735 |\n", "| total_timesteps | 9763528 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0205 |\n", "| n_updates | 298860 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27e+03 |\n", "| ep_rew_mean | 523 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40568 |\n", "| fps | 710 |\n", "| time_elapsed | 13737 |\n", "| total_timesteps | 9764600 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0192 |\n", "| n_updates | 298893 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.27e+03 |\n", "| ep_rew_mean | 523 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40572 |\n", "| fps | 710 |\n", "| time_elapsed | 13739 |\n", "| total_timesteps | 9766240 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0782 |\n", "| n_updates | 298944 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.29e+03 |\n", "| ep_rew_mean | 525 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40576 |\n", "| fps | 710 |\n", "| time_elapsed | 13741 |\n", "| total_timesteps | 9767936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0548 |\n", "| n_updates | 298997 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.29e+03 |\n", "| ep_rew_mean | 524 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40580 |\n", "| fps | 710 |\n", "| time_elapsed | 13743 |\n", "| total_timesteps | 9768992 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0369 |\n", "| n_updates | 299030 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.29e+03 |\n", "| ep_rew_mean | 525 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40584 |\n", "| fps | 710 |\n", "| time_elapsed | 13744 |\n", "| total_timesteps | 9769744 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0181 |\n", "| n_updates | 299054 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.29e+03 |\n", "| ep_rew_mean | 526 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40588 |\n", "| fps | 710 |\n", "| time_elapsed | 13745 |\n", "| total_timesteps | 9770424 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0211 |\n", "| n_updates | 299075 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.3e+03 |\n", "| ep_rew_mean | 526 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40592 |\n", "| fps | 710 |\n", "| time_elapsed | 13749 |\n", "| total_timesteps | 9773456 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0163 |\n", "| n_updates | 299170 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.31e+03 |\n", "| ep_rew_mean | 528 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40596 |\n", "| fps | 710 |\n", "| time_elapsed | 13750 |\n", "| total_timesteps | 9774304 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0209 |\n", "| n_updates | 299196 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.32e+03 |\n", "| ep_rew_mean | 530 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40600 |\n", "| fps | 710 |\n", "| time_elapsed | 13753 |\n", "| total_timesteps | 9776656 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00892 |\n", "| n_updates | 299270 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.32e+03 |\n", "| ep_rew_mean | 532 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40604 |\n", "| fps | 710 |\n", "| time_elapsed | 13754 |\n", "| total_timesteps | 9777368 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00498 |\n", "| n_updates | 299292 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.35e+03 |\n", "| ep_rew_mean | 537 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40608 |\n", "| fps | 710 |\n", "| time_elapsed | 13756 |\n", "| total_timesteps | 9778776 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0176 |\n", "| n_updates | 299336 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.37e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40612 |\n", "| fps | 710 |\n", "| time_elapsed | 13757 |\n", "| total_timesteps | 9779656 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.022 |\n", "| n_updates | 299364 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.37e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40616 |\n", "| fps | 710 |\n", "| time_elapsed | 13758 |\n", "| total_timesteps | 9780496 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0332 |\n", "| n_updates | 299390 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.38e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40620 |\n", "| fps | 710 |\n", "| time_elapsed | 13760 |\n", "| total_timesteps | 9782272 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0088 |\n", "| n_updates | 299445 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40624 |\n", "| fps | 710 |\n", "| time_elapsed | 13761 |\n", "| total_timesteps | 9783160 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0088 |\n", "| n_updates | 299473 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40628 |\n", "| fps | 710 |\n", "| time_elapsed | 13764 |\n", "| total_timesteps | 9784936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0394 |\n", "| n_updates | 299529 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40632 |\n", "| fps | 710 |\n", "| time_elapsed | 13768 |\n", "| total_timesteps | 9788200 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0137 |\n", "| n_updates | 299631 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40636 |\n", "| fps | 710 |\n", "| time_elapsed | 13769 |\n", "| total_timesteps | 9788592 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0297 |\n", "| n_updates | 299643 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40640 |\n", "| fps | 710 |\n", "| time_elapsed | 13770 |\n", "| total_timesteps | 9789528 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0119 |\n", "| n_updates | 299672 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40644 |\n", "| fps | 710 |\n", "| time_elapsed | 13771 |\n", "| total_timesteps | 9790344 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0411 |\n", "| n_updates | 299698 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40648 |\n", "| fps | 710 |\n", "| time_elapsed | 13773 |\n", "| total_timesteps | 9791720 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0575 |\n", "| n_updates | 299741 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40652 |\n", "| fps | 710 |\n", "| time_elapsed | 13774 |\n", "| total_timesteps | 9792656 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0116 |\n", "| n_updates | 299770 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40656 |\n", "| fps | 710 |\n", "| time_elapsed | 13775 |\n", "| total_timesteps | 9793248 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0185 |\n", "| n_updates | 299788 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 538 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40660 |\n", "| fps | 710 |\n", "| time_elapsed | 13776 |\n", "| total_timesteps | 9793968 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00565 |\n", "| n_updates | 299811 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.39e+03 |\n", "| ep_rew_mean | 536 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40664 |\n", "| fps | 710 |\n", "| time_elapsed | 13778 |\n", "| total_timesteps | 9795304 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0329 |\n", "| n_updates | 299853 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 536 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40668 |\n", "| fps | 710 |\n", "| time_elapsed | 13781 |\n", "| total_timesteps | 9797216 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.017 |\n", "| n_updates | 299912 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40672 |\n", "| fps | 710 |\n", "| time_elapsed | 13782 |\n", "| total_timesteps | 9797872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0938 |\n", "| n_updates | 299933 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40676 |\n", "| fps | 710 |\n", "| time_elapsed | 13784 |\n", "| total_timesteps | 9799816 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0065 |\n", "| n_updates | 299994 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40680 |\n", "| fps | 710 |\n", "| time_elapsed | 13785 |\n", "| total_timesteps | 9800560 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0401 |\n", "| n_updates | 300017 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40684 |\n", "| fps | 710 |\n", "| time_elapsed | 13787 |\n", "| total_timesteps | 9802264 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0645 |\n", "| n_updates | 300070 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 541 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40688 |\n", "| fps | 710 |\n", "| time_elapsed | 13788 |\n", "| total_timesteps | 9802904 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.039 |\n", "| n_updates | 300090 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 539 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40692 |\n", "| fps | 710 |\n", "| time_elapsed | 13790 |\n", "| total_timesteps | 9804272 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.011 |\n", "| n_updates | 300133 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 534 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40696 |\n", "| fps | 710 |\n", "| time_elapsed | 13791 |\n", "| total_timesteps | 9805000 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0183 |\n", "| n_updates | 300156 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 534 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40700 |\n", "| fps | 710 |\n", "| time_elapsed | 13793 |\n", "| total_timesteps | 9806320 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0285 |\n", "| n_updates | 300197 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 534 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40704 |\n", "| fps | 710 |\n", "| time_elapsed | 13794 |\n", "| total_timesteps | 9807064 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00624 |\n", "| n_updates | 300220 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.4e+03 |\n", "| ep_rew_mean | 534 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40708 |\n", "| fps | 710 |\n", "| time_elapsed | 13797 |\n", "| total_timesteps | 9809136 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0986 |\n", "| n_updates | 300285 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.41e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40712 |\n", "| fps | 710 |\n", "| time_elapsed | 13798 |\n", "| total_timesteps | 9809936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0458 |\n", "| n_updates | 300310 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40716 |\n", "| fps | 710 |\n", "| time_elapsed | 13799 |\n", "| total_timesteps | 9810960 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0258 |\n", "| n_updates | 300342 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 543 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40720 |\n", "| fps | 710 |\n", "| time_elapsed | 13801 |\n", "| total_timesteps | 9812536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0124 |\n", "| n_updates | 300391 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40724 |\n", "| fps | 710 |\n", "| time_elapsed | 13803 |\n", "| total_timesteps | 9813904 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0122 |\n", "| n_updates | 300434 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 549 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40728 |\n", "| fps | 710 |\n", "| time_elapsed | 13804 |\n", "| total_timesteps | 9814240 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0646 |\n", "| n_updates | 300444 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40732 |\n", "| fps | 710 |\n", "| time_elapsed | 13806 |\n", "| total_timesteps | 9816032 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00983 |\n", "| n_updates | 300500 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40736 |\n", "| fps | 710 |\n", "| time_elapsed | 13808 |\n", "| total_timesteps | 9817168 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0114 |\n", "| n_updates | 300536 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40740 |\n", "| fps | 710 |\n", "| time_elapsed | 13809 |\n", "| total_timesteps | 9818392 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0171 |\n", "| n_updates | 300574 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40744 |\n", "| fps | 710 |\n", "| time_elapsed | 13811 |\n", "| total_timesteps | 9819848 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00483 |\n", "| n_updates | 300620 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 548 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40748 |\n", "| fps | 710 |\n", "| time_elapsed | 13814 |\n", "| total_timesteps | 9821856 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.013 |\n", "| n_updates | 300682 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 552 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40752 |\n", "| fps | 710 |\n", "| time_elapsed | 13815 |\n", "| total_timesteps | 9822552 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.019 |\n", "| n_updates | 300704 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 544 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40756 |\n", "| fps | 710 |\n", "| time_elapsed | 13817 |\n", "| total_timesteps | 9823992 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00883 |\n", "| n_updates | 300749 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40760 |\n", "| fps | 710 |\n", "| time_elapsed | 13818 |\n", "| total_timesteps | 9824704 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.017 |\n", "| n_updates | 300771 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40764 |\n", "| fps | 710 |\n", "| time_elapsed | 13820 |\n", "| total_timesteps | 9826128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00759 |\n", "| n_updates | 300816 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 541 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40768 |\n", "| fps | 710 |\n", "| time_elapsed | 13823 |\n", "| total_timesteps | 9828128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0253 |\n", "| n_updates | 300878 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 541 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40772 |\n", "| fps | 711 |\n", "| time_elapsed | 13825 |\n", "| total_timesteps | 9829872 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0223 |\n", "| n_updates | 300933 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40776 |\n", "| fps | 711 |\n", "| time_elapsed | 13826 |\n", "| total_timesteps | 9830592 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0106 |\n", "| n_updates | 300955 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.43e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40780 |\n", "| fps | 711 |\n", "| time_elapsed | 13827 |\n", "| total_timesteps | 9831576 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0223 |\n", "| n_updates | 300986 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40784 |\n", "| fps | 711 |\n", "| time_elapsed | 13829 |\n", "| total_timesteps | 9833056 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0208 |\n", "| n_updates | 301032 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40788 |\n", "| fps | 711 |\n", "| time_elapsed | 13830 |\n", "| total_timesteps | 9833520 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0245 |\n", "| n_updates | 301047 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 546 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40792 |\n", "| fps | 711 |\n", "| time_elapsed | 13832 |\n", "| total_timesteps | 9834936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0303 |\n", "| n_updates | 301091 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40796 |\n", "| fps | 711 |\n", "| time_elapsed | 13833 |\n", "| total_timesteps | 9836168 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.029 |\n", "| n_updates | 301130 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40800 |\n", "| fps | 711 |\n", "| time_elapsed | 13835 |\n", "| total_timesteps | 9837504 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0121 |\n", "| n_updates | 301171 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 542 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40804 |\n", "| fps | 711 |\n", "| time_elapsed | 13837 |\n", "| total_timesteps | 9839136 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.024 |\n", "| n_updates | 301222 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 541 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40808 |\n", "| fps | 711 |\n", "| time_elapsed | 13838 |\n", "| total_timesteps | 9839856 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0448 |\n", "| n_updates | 301245 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.42e+03 |\n", "| ep_rew_mean | 541 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40812 |\n", "| fps | 711 |\n", "| time_elapsed | 13840 |\n", "| total_timesteps | 9840976 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.02 |\n", "| n_updates | 301280 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 540 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40816 |\n", "| fps | 711 |\n", "| time_elapsed | 13841 |\n", "| total_timesteps | 9841912 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00993 |\n", "| n_updates | 301309 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 539 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40820 |\n", "| fps | 711 |\n", "| time_elapsed | 13843 |\n", "| total_timesteps | 9842976 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0157 |\n", "| n_updates | 301342 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 539 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40824 |\n", "| fps | 711 |\n", "| time_elapsed | 13845 |\n", "| total_timesteps | 9844464 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0201 |\n", "| n_updates | 301389 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.45e+03 |\n", "| ep_rew_mean | 538 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40828 |\n", "| fps | 711 |\n", "| time_elapsed | 13846 |\n", "| total_timesteps | 9845768 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0104 |\n", "| n_updates | 301430 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 536 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40832 |\n", "| fps | 711 |\n", "| time_elapsed | 13848 |\n", "| total_timesteps | 9847360 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0107 |\n", "| n_updates | 301479 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.44e+03 |\n", "| ep_rew_mean | 537 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40836 |\n", "| fps | 711 |\n", "| time_elapsed | 13850 |\n", "| total_timesteps | 9848264 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0276 |\n", "| n_updates | 301508 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40840 |\n", "| fps | 711 |\n", "| time_elapsed | 13851 |\n", "| total_timesteps | 9849512 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.045 |\n", "| n_updates | 301547 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.46e+03 |\n", "| ep_rew_mean | 545 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40844 |\n", "| fps | 711 |\n", "| time_elapsed | 13854 |\n", "| total_timesteps | 9851160 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0142 |\n", "| n_updates | 301598 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 551 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40848 |\n", "| fps | 711 |\n", "| time_elapsed | 13855 |\n", "| total_timesteps | 9852552 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00875 |\n", "| n_updates | 301642 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 551 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40852 |\n", "| fps | 711 |\n", "| time_elapsed | 13858 |\n", "| total_timesteps | 9854160 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0238 |\n", "| n_updates | 301692 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.5e+03 |\n", "| ep_rew_mean | 552 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40856 |\n", "| fps | 711 |\n", "| time_elapsed | 13859 |\n", "| total_timesteps | 9855432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00673 |\n", "| n_updates | 301732 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 555 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40860 |\n", "| fps | 711 |\n", "| time_elapsed | 13861 |\n", "| total_timesteps | 9856856 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0177 |\n", "| n_updates | 301776 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 556 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40864 |\n", "| fps | 711 |\n", "| time_elapsed | 13864 |\n", "| total_timesteps | 9858848 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0134 |\n", "| n_updates | 301838 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 558 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40868 |\n", "| fps | 711 |\n", "| time_elapsed | 13866 |\n", "| total_timesteps | 9860424 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00562 |\n", "| n_updates | 301888 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 553 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40872 |\n", "| fps | 711 |\n", "| time_elapsed | 13867 |\n", "| total_timesteps | 9861448 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0161 |\n", "| n_updates | 301920 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.49e+03 |\n", "| ep_rew_mean | 558 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40876 |\n", "| fps | 711 |\n", "| time_elapsed | 13871 |\n", "| total_timesteps | 9863824 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.048 |\n", "| n_updates | 301994 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 563 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40880 |\n", "| fps | 711 |\n", "| time_elapsed | 13872 |\n", "| total_timesteps | 9864744 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0237 |\n", "| n_updates | 302023 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 567 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40884 |\n", "| fps | 711 |\n", "| time_elapsed | 13874 |\n", "| total_timesteps | 9866232 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00467 |\n", "| n_updates | 302069 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 567 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40888 |\n", "| fps | 711 |\n", "| time_elapsed | 13875 |\n", "| total_timesteps | 9867360 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00904 |\n", "| n_updates | 302104 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 566 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40892 |\n", "| fps | 711 |\n", "| time_elapsed | 13877 |\n", "| total_timesteps | 9868760 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0923 |\n", "| n_updates | 302148 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 564 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40896 |\n", "| fps | 711 |\n", "| time_elapsed | 13878 |\n", "| total_timesteps | 9869080 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0781 |\n", "| n_updates | 302158 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.49e+03 |\n", "| ep_rew_mean | 564 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40900 |\n", "| fps | 711 |\n", "| time_elapsed | 13881 |\n", "| total_timesteps | 9871192 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00629 |\n", "| n_updates | 302224 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 571 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40904 |\n", "| fps | 711 |\n", "| time_elapsed | 13882 |\n", "| total_timesteps | 9872104 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0157 |\n", "| n_updates | 302253 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 570 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40908 |\n", "| fps | 711 |\n", "| time_elapsed | 13883 |\n", "| total_timesteps | 9872936 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.017 |\n", "| n_updates | 302279 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.49e+03 |\n", "| ep_rew_mean | 565 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40912 |\n", "| fps | 711 |\n", "| time_elapsed | 13885 |\n", "| total_timesteps | 9874528 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0299 |\n", "| n_updates | 302328 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.49e+03 |\n", "| ep_rew_mean | 565 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40916 |\n", "| fps | 711 |\n", "| time_elapsed | 13887 |\n", "| total_timesteps | 9875736 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0259 |\n", "| n_updates | 302366 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.49e+03 |\n", "| ep_rew_mean | 565 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40920 |\n", "| fps | 711 |\n", "| time_elapsed | 13888 |\n", "| total_timesteps | 9876920 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00892 |\n", "| n_updates | 302403 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 568 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40924 |\n", "| fps | 711 |\n", "| time_elapsed | 13891 |\n", "| total_timesteps | 9878592 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0112 |\n", "| n_updates | 302455 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.48e+03 |\n", "| ep_rew_mean | 568 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40928 |\n", "| fps | 711 |\n", "| time_elapsed | 13892 |\n", "| total_timesteps | 9879560 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0117 |\n", "| n_updates | 302486 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 572 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40932 |\n", "| fps | 711 |\n", "| time_elapsed | 13893 |\n", "| total_timesteps | 9880192 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0181 |\n", "| n_updates | 302505 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.51e+03 |\n", "| ep_rew_mean | 574 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40936 |\n", "| fps | 711 |\n", "| time_elapsed | 13896 |\n", "| total_timesteps | 9882184 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0219 |\n", "| n_updates | 302568 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.52e+03 |\n", "| ep_rew_mean | 575 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40940 |\n", "| fps | 711 |\n", "| time_elapsed | 13898 |\n", "| total_timesteps | 9884032 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0442 |\n", "| n_updates | 302625 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 578 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40944 |\n", "| fps | 711 |\n", "| time_elapsed | 13901 |\n", "| total_timesteps | 9886128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0142 |\n", "| n_updates | 302691 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 577 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40948 |\n", "| fps | 711 |\n", "| time_elapsed | 13902 |\n", "| total_timesteps | 9887040 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0242 |\n", "| n_updates | 302719 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.54e+03 |\n", "| ep_rew_mean | 578 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40952 |\n", "| fps | 711 |\n", "| time_elapsed | 13903 |\n", "| total_timesteps | 9887760 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0209 |\n", "| n_updates | 302742 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.53e+03 |\n", "| ep_rew_mean | 582 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40956 |\n", "| fps | 711 |\n", "| time_elapsed | 13905 |\n", "| total_timesteps | 9889384 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0412 |\n", "| n_updates | 302793 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40960 |\n", "| fps | 711 |\n", "| time_elapsed | 13906 |\n", "| total_timesteps | 9890080 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.014 |\n", "| n_updates | 302814 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 591 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40964 |\n", "| fps | 711 |\n", "| time_elapsed | 13908 |\n", "| total_timesteps | 9891712 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00419 |\n", "| n_updates | 302865 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40968 |\n", "| fps | 711 |\n", "| time_elapsed | 13911 |\n", "| total_timesteps | 9893344 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00944 |\n", "| n_updates | 302916 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40972 |\n", "| fps | 711 |\n", "| time_elapsed | 13912 |\n", "| total_timesteps | 9894272 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0118 |\n", "| n_updates | 302945 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.57e+03 |\n", "| ep_rew_mean | 592 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40976 |\n", "| fps | 711 |\n", "| time_elapsed | 13913 |\n", "| total_timesteps | 9895288 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0396 |\n", "| n_updates | 302977 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.6e+03 |\n", "| ep_rew_mean | 593 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40980 |\n", "| fps | 711 |\n", "| time_elapsed | 13915 |\n", "| total_timesteps | 9896976 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0235 |\n", "| n_updates | 303030 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.61e+03 |\n", "| ep_rew_mean | 594 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40984 |\n", "| fps | 711 |\n", "| time_elapsed | 13916 |\n", "| total_timesteps | 9897680 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0244 |\n", "| n_updates | 303052 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.61e+03 |\n", "| ep_rew_mean | 594 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40988 |\n", "| fps | 711 |\n", "| time_elapsed | 13918 |\n", "| total_timesteps | 9899192 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0131 |\n", "| n_updates | 303099 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.6e+03 |\n", "| ep_rew_mean | 591 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40992 |\n", "| fps | 711 |\n", "| time_elapsed | 13920 |\n", "| total_timesteps | 9900696 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00864 |\n", "| n_updates | 303146 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.58e+03 |\n", "| ep_rew_mean | 586 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 40996 |\n", "| fps | 711 |\n", "| time_elapsed | 13923 |\n", "| total_timesteps | 9902208 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.015 |\n", "| n_updates | 303193 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.58e+03 |\n", "| ep_rew_mean | 585 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41000 |\n", "| fps | 711 |\n", "| time_elapsed | 13925 |\n", "| total_timesteps | 9904080 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0121 |\n", "| n_updates | 303252 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.61e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41004 |\n", "| fps | 711 |\n", "| time_elapsed | 13926 |\n", "| total_timesteps | 9904664 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0151 |\n", "| n_updates | 303270 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.63e+03 |\n", "| ep_rew_mean | 593 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41008 |\n", "| fps | 711 |\n", "| time_elapsed | 13927 |\n", "| total_timesteps | 9905680 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0293 |\n", "| n_updates | 303302 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 593 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41012 |\n", "| fps | 711 |\n", "| time_elapsed | 13931 |\n", "| total_timesteps | 9908160 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0366 |\n", "| n_updates | 303379 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 593 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41016 |\n", "| fps | 711 |\n", "| time_elapsed | 13932 |\n", "| total_timesteps | 9909120 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0358 |\n", "| n_updates | 303409 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.63e+03 |\n", "| ep_rew_mean | 597 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41020 |\n", "| fps | 711 |\n", "| time_elapsed | 13934 |\n", "| total_timesteps | 9910480 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00797 |\n", "| n_updates | 303452 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 594 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41024 |\n", "| fps | 711 |\n", "| time_elapsed | 13935 |\n", "| total_timesteps | 9911632 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0826 |\n", "| n_updates | 303488 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.63e+03 |\n", "| ep_rew_mean | 595 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41028 |\n", "| fps | 711 |\n", "| time_elapsed | 13937 |\n", "| total_timesteps | 9913184 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0122 |\n", "| n_updates | 303536 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 593 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41032 |\n", "| fps | 711 |\n", "| time_elapsed | 13940 |\n", "| total_timesteps | 9914832 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00644 |\n", "| n_updates | 303588 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 595 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41036 |\n", "| fps | 711 |\n", "| time_elapsed | 13942 |\n", "| total_timesteps | 9916864 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0138 |\n", "| n_updates | 303651 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 595 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41040 |\n", "| fps | 711 |\n", "| time_elapsed | 13943 |\n", "| total_timesteps | 9917720 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0198 |\n", "| n_updates | 303678 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.65e+03 |\n", "| ep_rew_mean | 599 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41044 |\n", "| fps | 711 |\n", "| time_elapsed | 13944 |\n", "| total_timesteps | 9918192 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0133 |\n", "| n_updates | 303693 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 606 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41048 |\n", "| fps | 711 |\n", "| time_elapsed | 13947 |\n", "| total_timesteps | 9920456 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0201 |\n", "| n_updates | 303764 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.67e+03 |\n", "| ep_rew_mean | 606 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41052 |\n", "| fps | 711 |\n", "| time_elapsed | 13949 |\n", "| total_timesteps | 9922080 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.101 |\n", "| n_updates | 303814 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 610 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41056 |\n", "| fps | 711 |\n", "| time_elapsed | 13950 |\n", "| total_timesteps | 9922728 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0095 |\n", "| n_updates | 303835 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 608 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41060 |\n", "| fps | 711 |\n", "| time_elapsed | 13952 |\n", "| total_timesteps | 9924352 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00902 |\n", "| n_updates | 303885 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 608 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41064 |\n", "| fps | 711 |\n", "| time_elapsed | 13954 |\n", "| total_timesteps | 9925400 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00996 |\n", "| n_updates | 303918 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 605 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41068 |\n", "| fps | 711 |\n", "| time_elapsed | 13956 |\n", "| total_timesteps | 9926840 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0483 |\n", "| n_updates | 303963 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 605 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41072 |\n", "| fps | 711 |\n", "| time_elapsed | 13958 |\n", "| total_timesteps | 9928824 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00626 |\n", "| n_updates | 304025 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 605 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41076 |\n", "| fps | 711 |\n", "| time_elapsed | 13960 |\n", "| total_timesteps | 9930008 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00671 |\n", "| n_updates | 304062 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 606 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41080 |\n", "| fps | 711 |\n", "| time_elapsed | 13962 |\n", "| total_timesteps | 9931648 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0254 |\n", "| n_updates | 304113 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 607 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41084 |\n", "| fps | 711 |\n", "| time_elapsed | 13963 |\n", "| total_timesteps | 9932376 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00924 |\n", "| n_updates | 304136 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.75e+03 |\n", "| ep_rew_mean | 611 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41088 |\n", "| fps | 711 |\n", "| time_elapsed | 13967 |\n", "| total_timesteps | 9934984 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0278 |\n", "| n_updates | 304218 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 612 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41092 |\n", "| fps | 711 |\n", "| time_elapsed | 13970 |\n", "| total_timesteps | 9937464 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00874 |\n", "| n_updates | 304295 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 612 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41096 |\n", "| fps | 711 |\n", "| time_elapsed | 13972 |\n", "| total_timesteps | 9938920 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00908 |\n", "| n_updates | 304341 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 615 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41100 |\n", "| fps | 711 |\n", "| time_elapsed | 13973 |\n", "| total_timesteps | 9939456 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0252 |\n", "| n_updates | 304357 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.75e+03 |\n", "| ep_rew_mean | 618 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41104 |\n", "| fps | 711 |\n", "| time_elapsed | 13973 |\n", "| total_timesteps | 9939800 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00745 |\n", "| n_updates | 304368 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.76e+03 |\n", "| ep_rew_mean | 614 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41108 |\n", "| fps | 711 |\n", "| time_elapsed | 13974 |\n", "| total_timesteps | 9940536 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0322 |\n", "| n_updates | 304391 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 603 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41112 |\n", "| fps | 711 |\n", "| time_elapsed | 13978 |\n", "| total_timesteps | 9943128 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0152 |\n", "| n_updates | 304472 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 603 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41116 |\n", "| fps | 711 |\n", "| time_elapsed | 13979 |\n", "| total_timesteps | 9944392 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00418 |\n", "| n_updates | 304512 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 603 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41120 |\n", "| fps | 711 |\n", "| time_elapsed | 13982 |\n", "| total_timesteps | 9946400 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0128 |\n", "| n_updates | 304574 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.73e+03 |\n", "| ep_rew_mean | 602 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41124 |\n", "| fps | 711 |\n", "| time_elapsed | 13983 |\n", "| total_timesteps | 9947280 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00782 |\n", "| n_updates | 304602 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.73e+03 |\n", "| ep_rew_mean | 600 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41128 |\n", "| fps | 711 |\n", "| time_elapsed | 13985 |\n", "| total_timesteps | 9948272 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.011 |\n", "| n_updates | 304633 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 596 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41132 |\n", "| fps | 711 |\n", "| time_elapsed | 13988 |\n", "| total_timesteps | 9950416 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0208 |\n", "| n_updates | 304700 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 596 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41136 |\n", "| fps | 711 |\n", "| time_elapsed | 13990 |\n", "| total_timesteps | 9951928 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0742 |\n", "| n_updates | 304747 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 596 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41140 |\n", "| fps | 711 |\n", "| time_elapsed | 13992 |\n", "| total_timesteps | 9953360 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0168 |\n", "| n_updates | 304792 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.72e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41144 |\n", "| fps | 711 |\n", "| time_elapsed | 13993 |\n", "| total_timesteps | 9954384 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0155 |\n", "| n_updates | 304824 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 584 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41148 |\n", "| fps | 711 |\n", "| time_elapsed | 13994 |\n", "| total_timesteps | 9955008 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0337 |\n", "| n_updates | 304843 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 581 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41152 |\n", "| fps | 711 |\n", "| time_elapsed | 13995 |\n", "| total_timesteps | 9956152 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.029 |\n", "| n_updates | 304879 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 585 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41156 |\n", "| fps | 711 |\n", "| time_elapsed | 13997 |\n", "| total_timesteps | 9957560 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0209 |\n", "| n_updates | 304923 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 585 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41160 |\n", "| fps | 711 |\n", "| time_elapsed | 14000 |\n", "| total_timesteps | 9959432 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0204 |\n", "| n_updates | 304982 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 584 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41164 |\n", "| fps | 711 |\n", "| time_elapsed | 14002 |\n", "| total_timesteps | 9960832 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0136 |\n", "| n_updates | 305025 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 585 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41168 |\n", "| fps | 711 |\n", "| time_elapsed | 14003 |\n", "| total_timesteps | 9962064 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00879 |\n", "| n_updates | 305064 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 581 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41172 |\n", "| fps | 711 |\n", "| time_elapsed | 14005 |\n", "| total_timesteps | 9963528 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.134 |\n", "| n_updates | 305110 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.71e+03 |\n", "| ep_rew_mean | 584 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41176 |\n", "| fps | 711 |\n", "| time_elapsed | 14008 |\n", "| total_timesteps | 9965704 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0127 |\n", "| n_updates | 305178 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.72e+03 |\n", "| ep_rew_mean | 588 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41180 |\n", "| fps | 711 |\n", "| time_elapsed | 14010 |\n", "| total_timesteps | 9967040 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0373 |\n", "| n_updates | 305219 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.75e+03 |\n", "| ep_rew_mean | 595 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41184 |\n", "| fps | 711 |\n", "| time_elapsed | 14012 |\n", "| total_timesteps | 9968696 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.01 |\n", "| n_updates | 305271 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.77e+03 |\n", "| ep_rew_mean | 594 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41188 |\n", "| fps | 711 |\n", "| time_elapsed | 14014 |\n", "| total_timesteps | 9970016 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0304 |\n", "| n_updates | 305312 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.77e+03 |\n", "| ep_rew_mean | 594 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41192 |\n", "| fps | 711 |\n", "| time_elapsed | 14015 |\n", "| total_timesteps | 9970800 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0146 |\n", "| n_updates | 305337 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.77e+03 |\n", "| ep_rew_mean | 599 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41196 |\n", "| fps | 711 |\n", "| time_elapsed | 14017 |\n", "| total_timesteps | 9972328 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0192 |\n", "| n_updates | 305385 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.76e+03 |\n", "| ep_rew_mean | 598 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41200 |\n", "| fps | 711 |\n", "| time_elapsed | 14019 |\n", "| total_timesteps | 9973992 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0331 |\n", "| n_updates | 305437 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.76e+03 |\n", "| ep_rew_mean | 597 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41204 |\n", "| fps | 711 |\n", "| time_elapsed | 14020 |\n", "| total_timesteps | 9974176 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00668 |\n", "| n_updates | 305442 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.76e+03 |\n", "| ep_rew_mean | 597 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41208 |\n", "| fps | 711 |\n", "| time_elapsed | 14022 |\n", "| total_timesteps | 9975720 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0169 |\n", "| n_updates | 305491 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.75e+03 |\n", "| ep_rew_mean | 596 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41212 |\n", "| fps | 711 |\n", "| time_elapsed | 14023 |\n", "| total_timesteps | 9976920 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0473 |\n", "| n_updates | 305528 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.74e+03 |\n", "| ep_rew_mean | 592 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41216 |\n", "| fps | 711 |\n", "| time_elapsed | 14026 |\n", "| total_timesteps | 9978760 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.129 |\n", "| n_updates | 305586 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.72e+03 |\n", "| ep_rew_mean | 590 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41220 |\n", "| fps | 711 |\n", "| time_elapsed | 14027 |\n", "| total_timesteps | 9979296 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.022 |\n", "| n_updates | 305602 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.73e+03 |\n", "| ep_rew_mean | 586 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41224 |\n", "| fps | 711 |\n", "| time_elapsed | 14028 |\n", "| total_timesteps | 9980608 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0114 |\n", "| n_updates | 305643 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.73e+03 |\n", "| ep_rew_mean | 586 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41228 |\n", "| fps | 711 |\n", "| time_elapsed | 14030 |\n", "| total_timesteps | 9981792 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.00616 |\n", "| n_updates | 305680 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.71e+03 |\n", "| ep_rew_mean | 579 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41232 |\n", "| fps | 711 |\n", "| time_elapsed | 14031 |\n", "| total_timesteps | 9982136 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0352 |\n", "| n_updates | 305691 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 577 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41236 |\n", "| fps | 711 |\n", "| time_elapsed | 14032 |\n", "| total_timesteps | 9983392 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0245 |\n", "| n_updates | 305730 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.7e+03 |\n", "| ep_rew_mean | 580 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41240 |\n", "| fps | 711 |\n", "| time_elapsed | 14034 |\n", "| total_timesteps | 9985096 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.12 |\n", "| n_updates | 305784 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 579 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41244 |\n", "| fps | 711 |\n", "| time_elapsed | 14036 |\n", "| total_timesteps | 9986336 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.012 |\n", "| n_updates | 305822 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.69e+03 |\n", "| ep_rew_mean | 581 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41248 |\n", "| fps | 711 |\n", "| time_elapsed | 14038 |\n", "| total_timesteps | 9987568 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0575 |\n", "| n_updates | 305861 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 579 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41252 |\n", "| fps | 711 |\n", "| time_elapsed | 14040 |\n", "| total_timesteps | 9988832 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0057 |\n", "| n_updates | 305900 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 580 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41256 |\n", "| fps | 711 |\n", "| time_elapsed | 14040 |\n", "| total_timesteps | 9989448 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0118 |\n", "| n_updates | 305920 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.67e+03 |\n", "| ep_rew_mean | 577 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41260 |\n", "| fps | 711 |\n", "| time_elapsed | 14043 |\n", "| total_timesteps | 9991040 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0603 |\n", "| n_updates | 305969 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.68e+03 |\n", "| ep_rew_mean | 577 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41264 |\n", "| fps | 711 |\n", "| time_elapsed | 14043 |\n", "| total_timesteps | 9991504 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0227 |\n", "| n_updates | 305984 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.64e+03 |\n", "| ep_rew_mean | 571 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41268 |\n", "| fps | 711 |\n", "| time_elapsed | 14045 |\n", "| total_timesteps | 9992488 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0124 |\n", "| n_updates | 306015 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.65e+03 |\n", "| ep_rew_mean | 570 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41272 |\n", "| fps | 711 |\n", "| time_elapsed | 14047 |\n", "| total_timesteps | 9993968 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0099 |\n", "| n_updates | 306061 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.65e+03 |\n", "| ep_rew_mean | 567 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41276 |\n", "| fps | 711 |\n", "| time_elapsed | 14049 |\n", "| total_timesteps | 9995808 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0214 |\n", "| n_updates | 306118 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.63e+03 |\n", "| ep_rew_mean | 565 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41280 |\n", "| fps | 711 |\n", "| time_elapsed | 14051 |\n", "| total_timesteps | 9996832 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.025 |\n", "| n_updates | 306150 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.64e+03 |\n", "| ep_rew_mean | 564 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41284 |\n", "| fps | 711 |\n", "| time_elapsed | 14051 |\n", "| total_timesteps | 9997472 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0209 |\n", "| n_updates | 306170 |\n", "----------------------------------\n", "----------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 3.62e+03 |\n", "| ep_rew_mean | 556 |\n", "| exploration_rate | 0.01 |\n", "| time/ | |\n", "| episodes | 41288 |\n", "| fps | 711 |\n", "| time_elapsed | 14054 |\n", "| total_timesteps | 9999208 |\n", "| train/ | |\n", "| learning_rate | 0.0001 |\n", "| loss | 0.0163 |\n", "| n_updates | 306225 |\n", "----------------------------------\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 7 } ], "source": [ "from stable_baselines3 import DQN\n", "from stable_baselines3.common.atari_wrappers import AtariWrapper\n", "from stable_baselines3.common.env_util import make_vec_env\n", "\n", "def make_env(n_envs=1):\n", " return make_vec_env(ENV, n_envs=n_envs, wrapper_class=AtariWrapper)\n", "\n", "env = make_env(n_envs=8)\n", "\n", "model = DQN(\n", " \"CnnPolicy\",\n", " env,\n", " learning_rate=1e-4,\n", " buffer_size=400_000,\n", " learning_starts=200_000,\n", " batch_size=32,\n", " tau=1.0,\n", " gamma=0.99,\n", " train_freq=4,\n", " gradient_steps=1,\n", " replay_buffer_class=None,\n", " replay_buffer_kwargs={\"handle_timeout_termination\": False},\n", " optimize_memory_usage=True,\n", " target_update_interval=30_000,\n", " exploration_fraction=0.1,\n", " exploration_initial_eps=1.0,\n", " exploration_final_eps=0.01,\n", " verbose=1,\n", ")\n", "model.learn(total_timesteps=10_000_000)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "vMliyZTFL3aV", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "d655fe88-04b2-495e-8d11-633c6c958167" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "698.0 +/- 166.63132958720578\n" ] } ], "source": [ "from stable_baselines3.common.evaluation import evaluate_policy\n", "\n", "eval_env = make_env()\n", "mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=IS_EVAL_DETERMINISTIC)\n", "print(f\"{mean_reward} +/- {std_reward}\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "H-HMy8-UM9Tk", "colab": { "base_uri": "https://localhost:8080/", "height": 338, "referenced_widgets": [ "b13f44315b814221b8ac58f781b8d8dc", "8b8326558d46419d83174ae89b883b2b", "82f8442ac69b41b6b6a8065e547b03c7", "b81f4b6541f84458932d8eb0228e7ef8", "d5356d552ed9423195f870691079b629", "886117612d324dac9bbabeee8fc97636", "e1fbcd58494a45b2b880eb38577725fb", "5d437a24cfba48dbb4498f91c68ba0d4", "fb23dea0a15e458493c80a4a05bcb987", "025b9573447c44839be54206e8c72546", "9449cb09deee4433badf7f23d54066dd", "c631f3d7414a4c85b1d90b0a6081ae0d", "2f131b76e9a245a8a70eaecec3a79dab", "ec4732db7e4341dca509fa103064f234", "0ef1c5036b934de4833619982d793a6e", "6c17ac1c17fa4e859766a8e94ec8b9a5", "bedc1f14e2ca4c66b0dbc36f61c838ed", "b4d66a382dd649a19f71dc240de0f738", "a22a68bf7e7e4243911049f457da9072", "f381936d4bf5412590d960dafff7fcd5", "1eebf027afea40a295580eaff4581ed6", "973456b6f6cc4cbaa47cc22c175a81e0", "20e53644609942528a5634a37acb7ee4", "5b6045a1b81d47a7a81679bc9467514e", "e1a7215f6e7d40e2a2f65e7a362d5ddb", "e9e3d538dd6545ad91e7e9d14f7aae7b", "563743d3454549979da65819262ea3f2", "20e83a90a5324f2ab1a39553019bbc21", "3f549a1f8c7f43528fbf1826f5d54db7", "64b83b90d3ef48579c2094e90e8bd0de", "ba6e86c492af4d01beefaac7012e31b2", "5896d2a0511b40e89e8dc4247380482a", "49987f2e5e0b4c7698d3ae23fbbc3ab6", "41bfeffe54fd4a89844e6ad4b2adfb7c", "512acd24ca4641cbbdd7513470dafd22", "8f883258af9f4f7ab2eb40c0d717ac9d", "b7ba55d377c9430485439f6ecd22fda1", "352e0f9710144f62ada3b4f242e16cd0", "b0c1c7a2018847d0bf280f850c180336", "318add55b7724e4cbd9bf826df1a214c", "195b63453e134a4bbdd1b3454433126d", "c9815c306d80407c99991bc1778d8227", "fe32f5dd9c4e48aaaa3ea2aedd3cfd88", "8e5d779840004fc0b0fe8009722931e1", "3e6a9805e868473d8ea26059bc3a5c3a", "8ee4e8d34c2a4960b00d5f520ebd2e45", "becde837748f4309b381e1f417b87d03", "b0053a1423384d0fa19e6481a2a6552a", "a1a676e828f545678f4e04e6cf430d02", "883956d1ce6343b39185944368d46fa9", "8e6364ae132a4e758579f263c6c2fde0", "4a72f73452034770914b0ec3adc0adf0", "3482b902e2864046b9e9ef4d8406709f", "4638a7ea88c44bd78cfd1e62c3073137", "9bd60bb4faff434e9c73860f45444ca2" ] }, "outputId": "52e0f961-a52a-4f04-8809-eb48f8cb1039" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[38;5;4mℹ This function will save, evaluate, generate a video of your agent,\n", "create a model card and push everything to the hub. It might take up to 1min.\n", "This is a work in progress: if you encounter a bug, please open an issue.\u001b[0m\n", "Saving video to /tmp/tmpksnmhmmy/-step-0-to-step-1000.mp4\n", "\u001b[38;5;4mℹ Pushing repo sgoodfriend/dqn-sb3-SpaceInvadersNoFrameskip-v4 to the\n", "Hugging Face Hub\u001b[0m\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "pytorch_variables.pth: 0%| | 0.00/431 [00:00