Initial commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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 +1,68 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 3102.39 +/- 50.41
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+---
+
+# **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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo sac --env AntBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo sac --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env AntBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## 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', 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', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - AntBulletEnv-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
+    - 2112781198
+  - - 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
+    - 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
+    - 64
+  - - use_sde
+    - true

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04be4b11664af450bdc7625fd734ed434c8098833acca1cbd084c4ca6c606d73
+size 1223740

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3102.3901204999997, "std_reward": 50.4136096909245, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:47:48.089767"}

sac-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d213b7ee79e82ff8279167236f06d2b131fb71b81747e1c33a5d51db6bb1cd4
+size 6034232

sac-AntBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

sac-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcc04c8ced0eb0115644eb0945e68f01a27cdb820c8a7003644d33c6c8a5178
+size 1100667

sac-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596c484c9a4d40148811adbe4046ff885aa5e35644e47482c9cf7e96e81c15da
+size 2179229

sac-AntBulletEnv-v0/data

@@ -0,0 +1,122 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 0x7f300de70710>",
+        "_build": "<function SACPolicy._build at 0x7f300de707a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f300de70830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f300de708c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f300de70950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f300de709e0>",
+        "forward": "<function SACPolicy.forward at 0x7f300de70a70>",
+        "_predict": "<function SACPolicy._predict at 0x7f300de70b00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f300de70b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f300de53ab0>"
+    },
+    "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",
+        "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\n   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 inf inf inf inf inf inf  1.]",
+        "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  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 False False\n False False False False  True]",
+        "_np_random": null,
+        "_shape": [
+            29
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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)",
+        "_shape": [
+            8
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621300.348797,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV/gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLHYaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUN0ht0EuafIzrrr/38/MvWuvOJld7rNv3G7trA+u7zXXDvLzKE9xw9lvaSM2b/NzEyjQhgxPVp3zr0SpO8/z58WvgVuFr2WS2c9m+XaP4UVZL6YhQo9OV0xOxJc2r8zvAo+AAAAAAAAAAAAAAAAAAAAAHe+fz+UdJRiLg=="
+    },
+    "_episode_num": 1029,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990016,
+    "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:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__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:\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    :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 0x7f300e2d2b90>",
+        "add": "<function ReplayBuffer.add at 0x7f300e2d2c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f300de397a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f300de39830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f300e3295d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

sac-AntBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6933c98aedb5b4d721372999e2f576cc7160e1035dcd603b472fea8fdabcc1d
+size 1255

sac-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595ad66693e3d0637bd187daf3ab7ee4d82c8def16dc7300fcd967d88728a238
+size 2731528

sac-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f330b5658e29c35a1791387a97ac793cb553d4bd7379059a83bcaf5f2dbb2cb
+size 747

sac-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb875e022a2ddee440ede17759e742ce6cef54dbb313b2bd5df092827744d5cd
+size 48561