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: 3436.13 +/- 14.91
+      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 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - AntBulletEnv-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
+    - 500000
+  - - 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
+    - 731695550
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - rl-trained-agents/sac-AntBulletEnv-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 +1,27 @@
+!!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 sha256:2bd14d084c7bb43375d2a237166e7af3c596e6f850f9b9d4da507af0a2f9ed04
+size 1285857

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3436.1275999, "std_reward": 14.909729299182679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T00:38:43.813814"}

sac-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9542a9cc1b904673a5414b7fe8a1bf86be1301d7e91be1f43e219fadbe91f319
+size 6021514

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 sha256:0b4ba7721e743c953e6aa5593d57a52670f05a9343420c7b1db4237deec9ddcc
+size 1099799

sac-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b66f6522ddda0e958d3f8ac037552f4a64a886f919f0b09a22d60fef683219
+size 2176234

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 0x7da47b6f8550>",
+        "_build": "<function SACPolicy._build at 0x7da47b6f85e0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7da47b6f8670>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7da47b6f8700>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7da47b6f8790>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7da47b6f8820>",
+        "forward": "<function SACPolicy.forward at 0x7da47b6f88b0>",
+        "_predict": "<function SACPolicy._predict at 0x7da47b6f8940>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7da47b6f89d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7da47b6f2200>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "num_timesteps": 300704,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1708903079341664422,
+    "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:": "gAWV5QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZwAAAAAAAAAJLHVr7hnjA9C8N/PzVIeT9haXc9/iqnPZzmy700jRK+jT9TvuyDlj45c2G/rMGCv5Zxij2CRMU+xWqBP63hJ70JYNs+ZZhVP+kcKD9XbAe/vAY1vxgbtL5fkgo/6Qx9PgAAAAAAAIA/AAAAAAAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLHIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 302,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.39859199999999995,
+    "_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": 1280696,
+    "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 0x7da47b614790>",
+        "add": "<function ReplayBuffer.add at 0x7da47b614820>",
+        "sample": "<function ReplayBuffer.sample at 0x7da47b6148b0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7da47b614940>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7da47b6149d0>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7da47b79f3c0>"
+    },
+    "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 sha256:3ca370f3eb0e8b6c422377ec64d9d6f467599f67f64e31f92a48865ca01bed7c
+size 1940

sac-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90be075425a4aa4386f0ea9b3c539408058a9218cddfa44e79a519a32a902fb
+size 2723961

sac-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9591e0e8d3482be236ace36693a8e7eef85dc7a6dca6386a965a7a76d7f1241e
+size 1180

sac-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.3.0a2
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa25ab3740b620a1ec39f028c08eed3bad0fb2910a8fdae5bf4aad209582c68
+size 11000