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 +1,77 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -178.65 +/- 102.84
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **Pendulum-v1**
+This is a trained model of a **TD3** 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 td3 --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --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 td3 --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('buffer_size', 200000),
+             ('gamma', 0.98),
+             ('gradient_steps', -1),
+             ('learning_rate', 0.001),
+             ('learning_starts', 10000),
+             ('n_timesteps', 20000),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('train_freq', [1, 'episode']),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+    - 3412888169
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Pendulum-v1__td3__3412888169__1670944265
+  - - 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 +1,24 @@
+!!python/object/apply:collections.OrderedDict
+- - - buffer_size
+    - 200000
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - -1
+  - - learning_rate
+    - 0.001
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 20000
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - train_freq
+    - - 1
+      - episode

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aeecde7fcc620f9861cea89f5d3bceba18175efa0fb10afec71fdd83eb9d784
+size 360484

results.json

@@ -0,0 +1 @@
+{"mean_reward": -178.64543199999997, "std_reward": 102.84157528038997, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:28:30.891997"}

td3-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb320293fb6b6947129baf9fc08b4500bab17775bb1ddd8c703305d8036da4f
+size 5925727

td3-Pendulum-v1/_stable_baselines3_version

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

td3-Pendulum-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238e6221c5f69ca9fee9e2d7321b311f8136bad5f6f42b1426032ecb13187c9d
+size 982447

td3-Pendulum-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd88a333b60ae872eebb3223752ee77e9d827162ec8c10c9ea6e98aa810cc83
+size 1971001

td3-Pendulum-v1/data

@@ -0,0 +1,126 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.td3.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TD3.\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 features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function TD3Policy.__init__ at 0x7fdcda3ed940>",
+        "_build": "<function TD3Policy._build at 0x7fdcda3ed9d0>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7fdcda3eda60>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7fdcda3edaf0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7fdcda3edb80>",
+        "forward": "<function TD3Policy.forward at 0x7fdcda3edc10>",
+        "_predict": "<function TD3Policy._predict at 0x7fdcda3edca0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7fdcda3edd30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fdcda3f1500>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "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:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWV6gAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAYWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWCAAAAAAAAACamZmZmZm5P5RoD0sBhZRoE3SUUpR1Yi4=",
+        "_mu": "[0.]",
+        "_sigma": "[0.1]"
+    },
+    "start_time": 1670944267449862132,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Pendulum-v1__td3__3412888169__1670944265/Pendulum-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAHvqfz/+6dE8J28jPpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 100,
+    "use_sde": false,
+    "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": 10000,
+    "buffer_size": 1,
+    "batch_size": 100,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.98,
+    "gradient_steps": -1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fdcda3ea430>",
+        "add": "<function ReplayBuffer.add at 0x7fdcda3ea4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fdcda3ea550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fdcda3ea5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fdcda3e4380>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 2,
+    "target_noise_clip": 0.5,
+    "target_policy_noise": 0.2,
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

td3-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfac2e52859cdce049d03e18e8d238e6d8448286f6161afb30fafc99bfce6cc
+size 2951289

td3-Pendulum-v1/pytorch_variables.pth

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

td3-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

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963f5444244addf195271dab09412d7b4f1e8c0f8addfbf33d4110489f1098f1
+size 2851