Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -215.13 +/- 126.97
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **Pendulum-v1**
+This is a trained model of a **A2C** agent playing **Pendulum-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo a2c --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env Pendulum-v1  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo a2c --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo a2c --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo a2c --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo a2c --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.9),
+             ('learning_rate', 'lin_7e-4'),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 8),
+             ('n_steps', 8),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('normalize_advantage', False),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-2, ortho_init=False)'),
+             ('use_rms_prop', True),
+             ('use_sde', True),
+             ('vf_coef', 0.4),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

a2c-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc6e37d6236b213dcb8c2af85150a21d45d74118bbf088db803d7597862dade
+size 100514

a2c-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

a2c-Pendulum-v1/data

@@ -0,0 +1,106 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f0ea1650d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0ea1650dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0ea1650e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0ea1650ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0ea1650f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0ea1652040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0ea16520d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0ea1652160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0ea16521f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0ea1652280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0ea1652310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0ea16523a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f0ea164e8c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
+        "log_std_init": -2,
+        "ortho_init": false,
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVBAwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAADAlGgKSwGFlIwBQ5R0lFKUjARoaWdolGgSKJYEAAAAAAAAAAAAAECUaApLAYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYBAAAAAAAAAAGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYBAAAAAAAAAAGUaCFLAYWUaBV0lFKUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUaC2MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMB01UMTk5MzeUjAVzdGF0ZZR9lCiMA2tleZRoEiiWwAkAAAAAAAAAAACAU8KznIcDtZNy7Ktb6Oay8s+2gdrVBu9hoTFNoGu1zNkT5hifdJx5L8ilG4DEeQFJng9D5F3gGJOSE1XM1EopZNIIlb400J5EcnoD8K2/CnObez7pYLEG2nUDRQtufdYWausENGaDt/P1pS9p70JjQ7Vc98J3UsxGRDctCIlu0I6ud/sYtoBPe575TzLsEti5jl6FqRnKrj12LWcrQoCexe7HH/UiAV1LzyQPzBlSZERXmHCdCvUSF7XpWt47xP9BzzqxX7aH3TPYWImqos1/ez/JlLdsD0MfMZl9G2CQq7cHHRlM3sj7jroA9c+pGt4l/iAGpRb80HbjwU71ykPTAVp531BXrc2qmIU6z9Fh4TAPx7fZ1kVF+L1Irlou+4Ckky7Ys59nB7KkciTI+N5jlb62ybZt0+ZWgIA6LKLvdx/mTQtB4k1aplT/C7L9/ybKCFn2quN/7YlIkxoH1U0xdabG6rgOrR+SHMmvUwvtKB+19Ibb07mSgVQyjNAvnyADPJf3pkxylZtn7f/OVpWEaWfl6BcLwy0grrEgUK+H+8P8XWMuBginXgwzn3sy4+ZOlr45op6TtuqX0Knz/SySGDlBIK8JqKObzB6fGt+ovJHEM8KlL4veKwkLkuuMWBaex3FBdWskry5qhslxMgnk2thh8DaXmAfbuI8j0SqHMW1kleITi9ekfXx/eSi5hX1GjA/M62Zixuay1H8zH9VjsTRcGacyJ0vh1hNReDFoNsXFbLfLqaIvbLDQjY7T289ZXsupvAxu2GVTbqWst+ckPPzwH7vLikULC+weAKwxarqm+ugAXgyz774meHOsvQYuu18nvrrunjZWDvwaKuYohEwUfSnpotE9XhX99yUTc8sGPQidTfXkzm/t8MWP8it4l4VSEgDLn8GW8t2DAh8EwFa/KOGoZEGjYqZ2IMA70E+F2LqgaZlQLFMONTIx3yuN5F2e1MT4v2wdBRK9R+lGMpxIiNldyOwwxLDBTRDMhd7APidmDwQBnvaIecKFa95btwHkRBEUT5g++/I0DDg685EX4OMO2YtTPqM3PQluS4puEhAQRVukNGSh4gYDgcBPKZl4ThNf+G+E7El9fmWJcP39Sifw6Mn+GEisM1RhHY05XZHUv5W4r8kD2jSLMY+IIL2+LtQrW7it7y28+sEicLoEfYOky9ZJF6l0fR+sXEawf+REH9LvtRJ4yzfxr7KisNpr1axv1ae5CDXS+XTzuOG/BJnHvt8arnY1XWH9SdkCOeok6MI8GBCtjTCxJ5JbpI5J0i0A66mJaRW9LMfP6Cil3/cVRQ9uN2KTtV3o7rJwY4XCnj7DJmqrUwofDDl7Ek0PoN7w0Hh8YHOy8qhPw7V8ALdjZn7eYtjCQIldQvHbM1I73RtCLQvQGFMXUCJ022pGRqTvZX5XWSizqbgX6TJmI6LDF9wcpYealB7cDwelfqdpzHRmyjRbIX9b+w4uj//aDRgP2SgiOAq/D/9/0SbgK/E0FQyclhNVAkbKwXhAxKGczpvJow0mFFUAt/5fT5KAsmQTAt8p0FsrGMDTfk4RzZgqZSm+ihVRS371Tx3twpGA1goo/AIfJh8slJC3hkR1OGCN7LAPGCwbM9rHlKSU4uuhJiff196h9q1kPMld6989MfKLVkvCl7ofCRurPUW46ceJKE951sQD1v8cK0HK1JmuBTCXAelCUCIFNLGk3tMXNVmuuFF3o3xb4V4T1IAYIfBdyEVHhIIZOE/JEY79daQw8njYEtQ6YwZ6kNCBYfrjq2OglITcRdwDmINL42ro6HnbWgLZQ8Ce/EiPVBtWHwhvGUHK1FNONzRzXgT1zKEg+WAigeuK4QVIxdITM4YvUyYvpQJuJd+xGD1no7BYIKXdV4aDlsRnWSMmS+zTyTvC0+TgBMCNpMvdChjaB/XTrMVsm0vgPmCYswn067MTYWfm5oCqqmNciqoRfFL2O2mxFT1VMcKDrxHBdBUhSG5UmAerx86KAEytbsCbn6OOj8Y02VwVynzXd0WJfLioeGMZISM1eneWfTc1mQ6CpdDxJqUmU86/KsBL3Bb0S2NAqFysFJZKxDwLej8xz+xH8IxEHzlkiiNH+2IIq0663FAwi6wg6dgcryDqQ+lNDwn898nylrcYShigDrtrFBNezKx3ZjpkPCnPUeQB4hJUrYCUJy5CyytC/x1UsByKez/aSNEWnlWnzYdJf2PoKL0YfmaR3KpXzi9ax3BHPgk1cdmgdVkqevFJ0DUdTBFQj/mhaKqcaT0rKJLgy/11AhWW4nX7+kAdgR0b1iAseI0TbMDtohBuqqUZfqMfUKsdI8v2aeUd0+IqOjPBFe7TZRC7OUYmf789SRTpw9gst4tzx7tLap8JnFt2keKhqd3vBgqpvlsxvx0DcPC+bo/qIldKiAn5D7TPjeWLzJ1gmpk1mVKOyWOv/ZzlRTfe8yEsMsRcgdPxbOuxLjlOwo1uFh9NjHoOz/xbnI62I49ZzT59GUCNtAL74UqjlRoyXZ5ELEjhTn+F5fYfEkY2TnSsgKO4Wwb/xD41S4mBL7LcUyF76ybV7Yx0L6V2QGoSfyhHFqMQJs/haLPPW18mWJb/UDl90ZN9TEzcdXvZsmCeqzCagC6YDHp3fop+5nAQSnT/Byt2j7z+6cnl/aZh6oKs5xrEMmuzpLFbXNVof9hNmX5E0DQ2M8uBqqeW95p6z8ySnOxURAO28oYWsbVyeYaNlWLZrOtIMZDRjjbecSSwMLlrBhw4mZVht4DgOQxI1+P7sPHZLMf89U+5ctf1rD0r1AXgyXjzOxKvCxWMhrz6Ah19+zal/bAIpw+0V7Pq85PRQO4UeScmMwODR8jcOfILuMmo7xXhemY/JqtOncklEaGapMeGlkiefvQkx9L5EWvLn6stI4zRP4pZXx9iOz17IKJmKOVHgCIAOiheb0bwkjNkItlfYO3LzeLLPuBDNLFg7tQu5NPWy28a4nBsE/gsyEteRvF2ECYFIOJg06dzc77IWw7o+z1Q5APxLg9uvyFniYWNuJyk7rflLCmYcg1gN657CWff8YfPr0ukKOamco94X1nFdyroxHiQlRXaP91DOqMueI1pCasyRQt0jtbWwxdEVyzP3GzUZXBWqa0xXCzwe29cxg2aiwKuuAAVfaCE/Pt1cJXq8wvliF81sMDPMbowd9+uyWuExq/e+2W3wWeV3hVofoiEySjBrJPWVJW9++UocJbC0ppNw5mtHktkZqUk6kVtUgVQ4Cj4udj/bluZzcqWjIvOCJO52M+xcQY808Ei8T/lwwS9TguuzQ3e0KR7hptgNcX1/XhCvAuUaAeMAnU0lImIh5RSlChLA2gLTk5OSv////9K/////0sAdJRiTXAChZRoFXSUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1671036488097593589,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Pendulum-v1__a2c__1652316985__1671036485/Pendulum-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAABrxkj0YV38/9/9tP4SgdL+G6ZY+g6NxP85PND79/3s/wp/Wvo3q8j5XWmE/DIYQvQySN75W2ns/HxktPr0hez/Lv0a+VWFiPx8Idj/Fe42+Vl0mv3oKkb5og3U/n1fVvJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLCEsDhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 15625,
+    "n_steps": 8,
+    "gamma": 0.9,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.0,
+    "vf_coef": 0.4,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false
+}

a2c-Pendulum-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ef8e6d1ccbc84a9eb7f38039a9feb4482aa45ea32a0b5162684cb84fdd6138
+size 39806

a2c-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9de0c880f7a2c6ffe38cdc71ba4a95c4f3e0f4a630220a634b198d1ca3c44f
+size 40510

a2c-Pendulum-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

a2c-Pendulum-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1652316985
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Pendulum-v1__a2c__1652316985__1671036485
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,31 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.9
+  - - learning_rate
+    - lin_7e-4
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 8
+  - - n_steps
+    - 8
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - normalize_advantage
+    - false
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False)
+  - - use_rms_prop
+    - true
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.4

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1725b8b5e6454751ff51b4a647e87a1a5f1afa62d308aeedcef6afca93ee1771
+size 174208

results.json

@@ -0,0 +1 @@
+{"mean_reward": -215.13314810000003, "std_reward": 126.97463762723024, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:54:11.918876"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2490e5b885982d76beda499622d0f2adfa827a3cefef9859e40592b4a12716d5
+size 141974

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225bd9125535be43c14f98b631de80ab709c4407dae0e2a626455e638acd654b
+size 4165