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 +1,85 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2DBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2DBulletEnv-v0
+      type: Walker2DBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 2674.29 +/- 5.47
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **Walker2DBulletEnv-v0**
+This is a trained model of a **TQC** 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 tqc --env Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo tqc --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 tqc --env Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Walker2DBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env Walker2DBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env Walker2DBulletEnv-v0 -f logs/ -orga Emperor-WS
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 'lin_7.3e-4'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - Walker2DBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1908048640
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - env_wrapper
+    - sb3_contrib.common.wrappers.TimeFeatureWrapper
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - lin_7.3e-4
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3, net_arch=[400, 300])
+  - - tau
+    - 0.02
+  - - train_freq
+    - 64
+  - - use_sde
+    - true

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:ac03f121883d65cfac4a693a072b4241a43136f85ac123acc7b45b8499b68888
+size 1122852

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2674.2946613, "std_reward": 5.469212969134861, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-29T21:55:54.520702"}

tqc-Walker2DBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bd3a6b586cf711ceb75d66ce0bbd4c6d9f059439dcbc1fbf2e342236275a9e
+size 6122053

tqc-Walker2DBulletEnv-v0/_stable_baselines3_version

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

tqc-Walker2DBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399a531238f8afc8a9f6542210d28a6a670981907fae11af1495764b2787e5e0
+size 1073879

tqc-Walker2DBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcffaf85701bc2bbf18400e06514b709e422664102f17381e6c2d0599661c0f5
+size 2246378

tqc-Walker2DBulletEnv-v0/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__annotations__": "{'actor': <class 'sb3_contrib.tqc.policies.Actor'>, 'critic': <class 'sb3_contrib.tqc.policies.Critic'>, 'critic_target': <class 'sb3_contrib.tqc.policies.Critic'>}",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature 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_quantiles: Number of quantiles for the critic.\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 TQCPolicy.__init__ at 0x7d5526f8f370>",
+        "_build": "<function TQCPolicy._build at 0x7d5526f8f400>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7d5526f8f490>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7d5526f8f520>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7d5526f8f5b0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7d5526f8f640>",
+        "forward": "<function TQCPolicy.forward at 0x7d5526f8f6d0>",
+        "_predict": "<function TQCPolicy._predict at 0x7d5526f8f760>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7d5526f8f7f0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d5526f79c00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621441.9669518,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV0QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZcAAAAAAAAANFCmL4AAAAAAACAP443RD8AAAAAQpN8vAAAAABI6na/QwKAP6+uD7rqrxu9T5I4P9pCHT9pdLs+JkAwPfglrjurCqg+0/EEvixfxj6xav++AAAAAAAAgD83iQE/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSxeGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 2892,
+    "use_sde": true,
+    "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": 990016,
+    "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  True]",
+        "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  True]",
+        "_shape": [
+            23
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf   0.]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf  1.]",
+        "low_repr": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf   0.]",
+        "high_repr": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf  1.]",
+        "_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": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 64,
+    "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 0x7d552821a440>",
+        "add": "<function ReplayBuffer.add at 0x7d552821a4d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7d552821a560>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7d552821a5f0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d552821a680>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d5528195600>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "remove_time_limit_termination": false,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-Walker2DBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff5d4192fc6c9b4e2c10d2bccca0a83d16838cf1e9ae8f737d5acc566c604a0
+size 1940

tqc-Walker2DBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d44cf1f919de26a088b2104b70c04b3333c395d53565e634bc52e38e36f7a2
+size 2781433

tqc-Walker2DBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d161de64452f3a3d852fbe17a6764089638e52ececa8e22500b64f873b4b13b
+size 1180

tqc-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:c963d3e7ace1cb88910dc419d4cd61c37a396d3c64ec8f45d809c672723308a6
+size 95481