Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,82 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2DBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2DBulletEnv-v0
+      type: Walker2DBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 2550.10 +/- 14.80
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **Walker2DBulletEnv-v0**
+This is a trained model of a **TD3** agent playing **Walker2DBulletEnv-v0**
+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 Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2DBulletEnv-v0  -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 Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2DBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env Walker2DBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env Walker2DBulletEnv-v0 -f logs/ -orga Emperor-WS
+```
+
+## Hyperparameters
+```python
+OrderedDict([('buffer_size', 200000),
+             ('gamma', 0.98),
+             ('gradient_steps', -1),
+             ('learning_rate', 0.001),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('train_freq', [1, 'episode']),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Walker2DBulletEnv-v0
+  - - 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
+    - 1035828328
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Walker2DBulletEnv-v0__td3__1035828328__1672252942
+  - - 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
+    - 1000000.0
+  - - 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 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7929f218571b955bf9942dcf8643834aa51b30feaf4110075b921dfd7e9abff9
+size 1102795

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2550.1013432, "std_reward": 14.801990800602246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-02T17:02:32.124368"}

td3-Walker2DBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56d24f7dad09d9cb1386495c7d66643424193ae27b325614867396ee35c64f6
+size 6376308

td3-Walker2DBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.0a2

td3-Walker2DBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4375e17a95f1288a42519190a38dcc94b8173a2afb641058afe493e7e6f8ec1
+size 1055520

td3-Walker2DBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d4c123385e523d767df6a40e23a202084ed5018cacc067d0865129c38a676d
+size 2124522

td3-Walker2DBulletEnv-v0/data

@@ -0,0 +1,134 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.td3.policies",
+        "__annotations__": "{'actor': <class 'stable_baselines3.td3.policies.Actor'>, 'actor_target': <class 'stable_baselines3.td3.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
+        "__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 0x7ae480dae4d0>",
+        "_build": "<function TD3Policy._build at 0x7ae480dae560>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7ae480dae5f0>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7ae480dae680>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7ae480dae710>",
+        "forward": "<function TD3Policy.forward at 0x7ae480dae7a0>",
+        "_predict": "<function TD3Policy._predict at 0x7ae480dae830>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7ae480dae8c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ae480db0b40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "num_timesteps": 1000339,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVOgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWMAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwaFlIwBQ5R0lFKUjAZfc2lnbWGUaAgoljAAAAAAAAAAmpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/lGgPSwaFlGgTdJRSlHViLg==",
+        "_mu": "[0. 0. 0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1 0.1 0.1]"
+    },
+    "start_time": 1672252945185227909,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Walker2DBulletEnv-v0__td3__1035828328__1672252942/Walker2DBulletEnv-v0",
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAA2MpL4AAAAAAACAPzNdZD8AAAAAlMjeuwAAAAAVNFO/NHf8u/z5Db7DPNY+K7sePnxtAj4V7jS/FgCAPyYZWre4gEm9RluovZkEgD9fXUS6AACAPwAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLFoaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2796,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00033900000000008923,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990341,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False]",
+        "_shape": [
+            22
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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 0x7ae480cfa440>",
+        "add": "<function ReplayBuffer.add at 0x7ae480cfa4d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7ae480cfa560>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7ae480cfa5f0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7ae480cfa680>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ae480e70940>"
+    },
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

td3-Walker2DBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d559db5be836d8dff8235c888b883eef4a3f5f1ffe447c465d14d813929f81
+size 3177642

td3-Walker2DBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

td3-Walker2DBulletEnv-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
+- Python: 3.10.13
+- Stable-Baselines3: 2.3.0a2
+- PyTorch: 2.1.2+cpu
+- GPU Enabled: False
+- Numpy: 1.26.3
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.0
+- OpenAI Gym: 0.26.2

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbcaa8b94db102eae3ee5e0b18701f30b7ed6b0e99ffad294d106411f6c157a
+size 76742