Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,79 @@
+---
+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: 3567.83 +/- 35.65
+      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 qgallouedec -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 qgallouedec -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 qgallouedec
+```
+
+## 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)])
+```

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 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4800f4c67e472ef097196206c7ad54a34750cd74c91532436b2cd3a4f38cb2dc
+size 1282014

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3567.8325654, "std_reward": 35.645627418113534, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:32:24.755241"}

sac-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1dcbe61d16389d13bd9c30896bee7a21d058be9a3b0f9a682ebd0924bf882ae
+size 6021870

sac-AntBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

sac-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d693a6d4d085975c383e796ec674d8dd6187475f66871e28fde475a68c155b9e
+size 1099366

sac-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e5171e99f1fda123a15cbc782093053cdd6e331f6939169f76512b9ce4675c
+size 2175801

sac-AntBulletEnv-v0/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__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 0x7ffb21d11ca0>",
+        "_build": "<function SACPolicy._build at 0x7ffb21d11d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7ffb21d11dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7ffb21d11e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7ffb21d11ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7ffb21d11f70>",
+        "forward": "<function SACPolicy.forward at 0x7ffb21d1a040>",
+        "_predict": "<function SACPolicy._predict at 0x7ffb21d1a0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7ffb21d1a160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ffb21d19a80>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_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]",
+        "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]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "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",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "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",
+        "__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 0x7ffb21d6a430>",
+        "add": "<function ReplayBuffer.add at 0x7ffb21d6a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7ffb21d6a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7ffb21d6a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ffb221f2c00>"
+    },
+    "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,
+    "_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:ff49323bc5e96fe515ea474232a9b8eeb9a7c3bc8c84e2cd8cec3d026403cb3e
+size 1507

sac-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8ce2dabd4d43cea0c4c65411cffa91d03d8bc7ea2e5ab0308fdced027915a8
+size 2723528

sac-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6aa97c6e9e001689b86525a25258069238223f274c1b873cc9bfbc819a86418
+size 747

sac-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a8a22100459d703097f9b3ee51709859c4e6c9e01fdfd24a437d1b5371095c
+size 34573