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 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 3578.87 +/- 26.38
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **SAC** agent playing **AntBulletEnv-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 sac --env AntBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo sac --env AntBulletEnv-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 sac --env AntBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo sac --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env AntBulletEnv-v0 -f logs/ -orga Emperor-WS
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.98),
+             ('gradient_steps', 8),
+             ('learning_rate', 0.00073),
+             ('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', 8),
+             ('use_sde', True),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - AntBulletEnv-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
+    - 3073263478
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/AntBulletEnv-v0__sac__3073263478__1671835214
+  - - 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 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 8
+  - - learning_rate
+    - 0.00073
+  - - 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
+    - 8
+  - - 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 sha256:5c9d4a9e7624f5246ccf4804ffdeef71d402e7b72ac30fc014ec0d647008cb8c
+size 1283285

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3578.8669053999997, "std_reward": 26.376790006591403, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-01T22:40:51.395086"}

sac-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb758a93d498d87de7e6e340088a52b7a81a6ebf86b441f392821863866ea21
+size 6020380

sac-AntBulletEnv-v0/_stable_baselines3_version

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

sac-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639d73698448222fac9b513bf51be50ad723afaa5fea7d9121a0f7ff23993bd9
+size 1099607

sac-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50a59fc6c48abd6ac5361d5c2bc52fc1a4d0b48d90329ccf93a1410a6ea8795
+size 2175722

sac-AntBulletEnv-v0/data

@@ -0,0 +1,138 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__annotations__": "{'actor': <class 'stable_baselines3.sac.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 SAC.\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 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 SACPolicy.__init__ at 0x7fa5c6bd2200>",
+        "_build": "<function SACPolicy._build at 0x7fa5c6bd2290>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fa5c6bd2320>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fa5c6bd23b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fa5c6bd2440>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fa5c6bd24d0>",
+        "forward": "<function SACPolicy.forward at 0x7fa5c6bd2560>",
+        "_predict": "<function SACPolicy._predict at 0x7fa5c6bd25f0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fa5c6bd2680>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa5c6bd7840>"
+    },
+    "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": 1671835216851530424,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/AntBulletEnv-v0__sac__3073263478__1671835214/AntBulletEnv-v0",
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV5QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZwAAAAAAAAADs1ar7Q0ni994Z/P2+7DD+Jpx++bUctvsi5vDy/8AW+dxc4PztWHL/vWTO9/nagPjUdgL+7/ba6EzTgPi88UT0QBUG/Eho2v+/aYD+3ZwU/QkWWvjO7wL613Ha/JJ5kPgAAgD8AAAAAAACAPwAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLHIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 1019,
+    "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": 990000,
+    "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 False False\n 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 False False\n False False False False]",
+        "_shape": [
+            28
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -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 inf inf 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  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 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": 8,
+    "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 0x7fa5c6b06440>",
+        "add": "<function ReplayBuffer.add at 0x7fa5c6b064d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fa5c6b06560>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fa5c6b065f0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fa5c6b06680>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa59b5364c0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLCGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_action_repeat": [
+        null
+    ],
+    "surgeon": null,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "_last_action": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHVHdL8NsXe/8pp3v8Avb7+1xnq/GFl1v4o8br90Eno/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    }
+}

sac-AntBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa91b17f2aab2d7499b05ab92ed66375fe55cbe3cb3265c886da5a133434806
+size 1940

sac-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79666fa26f4ebebd552e79c056235bb7b2880eaccdf5d92d6a766982a769ba0d
+size 2723513

sac-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e2ef326731bc4a6d25a63632b26bcdf508a737f26c6c6880c86f2b7be13625
+size 1180

sac-AntBulletEnv-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:cc2df9cf20e96ea7c3adbacda9a6086a2f97405ba3661049da23f1d9c02f5973
+size 34573