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 +1,83 @@
+---
+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: 2280.24 +/- 566.59
+      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([('batch_size', 256),
+             ('buffer_size', 200000),
+             ('gamma', 0.98),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0007),
+             ('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),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Walker2DBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_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
+    - 600000
+  - - 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
+    - 2253046436
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - rl-trained-agents/td3/Walker2DBulletEnv-v0_1/Walker2DBulletEnv-v0.zip
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 200000
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0007
+  - - 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

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:cfe60b2e56223656a01a4f44b1512dbdbeadda3b3b0fb2e25d31e8d7be53f840
+size 1079359

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2280.2354861, "std_reward": 566.5869815252843, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T18:13:52.775860"}

td3-Walker2DBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea13926535bfb4d8c538cd51c993e57382eac2638e2d95e5053203467fb6f619
+size 6377441

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 sha256:7102001e0f8061cacf97e3c3e0779807b10cd1a9ae0a9d120c5bdb800d804e72
+size 1055712

td3-Walker2DBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcc66586db9bbc0246aea70e43f58ea8841e4544b7df91b1ff78277dcd53ebb
+size 2125034

td3-Walker2DBulletEnv-v0/data

@@ -0,0 +1,135 @@
+{
+    "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 0x7f61d2dd53f0>",
+        "_build": "<function TD3Policy._build at 0x7f61d2dd5480>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f61d2dd5510>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f61d2dd55a0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f61d2dd5630>",
+        "forward": "<function TD3Policy.forward at 0x7f61d2dd56c0>",
+        "_predict": "<function TD3Policy._predict at 0x7f61d2dd5750>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f61d2dd57e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f61d2dcf280>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "num_timesteps": 600000,
+    "_total_timesteps": 600000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVUQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWMAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwaFlIwBQ5R0lFKUjAZfc2lnbWGUaAgoljAAAAAAAAAAmpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/lGgPSwaFlGgTdJRSlIwGX2R0eXBllGgKjAdmbG9hdDMylJOUdWIu",
+        "_mu": "[0. 0. 0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1 0.1 0.1]",
+        "_dtype": "<class 'numpy.float32'>"
+    },
+    "start_time": 1709052081407180069,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAF05v74AAAAAAACAPyHdBD8AAAAAUBRLvQAAAAC1LWC/TNvBPkgknz7EFHa+k0icvhe1PT/rH8k+3iQOPw//KL9iIBm+HG2ZPvdVgT+hcSs7AAAAAAAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLFoaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 1685,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_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": 1580341,
+    "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": 256,
+    "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 0x7f619ad41360>",
+        "add": "<function ReplayBuffer.add at 0x7f619ad413f0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f619ad41480>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f619ad41510>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f619ad415a0>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f619acc4780>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "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:fe398a362477677bd7cf573823ee556af815783169cf0c2b0c6db2997fe0d1ee
+size 3178154

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
+- GPU Enabled: True
+- Numpy: 1.26.3
+- Cloudpickle: 3.0.0
+- 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 sha256:5776e272929342c76f3a989ea7d5e209fabc9ad0c4f05c7e05d007a5c52b1a58
+size 46648