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:
+- seals/Walker2d-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Walker2d-v1
+      type: seals/Walker2d-v1
+    metrics:
+    - type: mean_reward
+      value: 5665.26 +/- 225.00
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **seals/Walker2d-v1**
+This is a trained model of a **SAC** agent playing **seals/Walker2d-v1**
+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 seals/Walker2d-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Walker2d-v1  -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 seals/Walker2d-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Walker2d-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env seals/Walker2d-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env seals/Walker2d-v1 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 100000),
+             ('gamma', 0.99),
+             ('learning_rate', 0.0005845844772048097),
+             ('learning_starts', 1000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'log_std_init': 0.1955317469998743,
+               'net_arch': [400, 300],
+               'use_sde': False}),
+             ('tau', 0.02),
+             ('train_freq', 1),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - hyperparams/python/sac.py
+  - - device
+    - cpu
+  - - env
+    - seals/Walker2d-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - 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
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3467367905
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - buffer_size
+    - 100000
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - 0.0005845844772048097
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - log_std_init: 0.1955317469998743
+      net_arch:
+      - 400
+      - 300
+      use_sde: false
+  - - tau
+    - 0.02
+  - - train_freq
+    - 1

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 sha256:00ad2e9ea7838a21e6948efcb3539a388a221d6ca55101787a0897965740a87c
+size 1302151

results.json

@@ -0,0 +1 @@
+{"mean_reward": 5665.262325600001, "std_reward": 225.0045407158244, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:50:27.998344"}

sac-seals-Walker2d-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ac45c9e851f7692927063f27c4982f4cb943a0a7de4628db8fefb1f5a246bd
+size 5802152

sac-seals-Walker2d-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.0a3

sac-seals-Walker2d-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed19e78ea4869891dae1c4d56c6234abc88480ee2a5389c43b654d855dff9b7
+size 1058141

sac-seals-Walker2d-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf58c24f88beab41bc512cab0873a12e81926c402c2fb51e22582468f7c2c106
+size 2098489

sac-seals-Walker2d-v1/data

@@ -0,0 +1,129 @@
+{
+    "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 0x7f7d930df700>",
+        "_build": "<function SACPolicy._build at 0x7f7d930df790>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f7d930df820>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f7d930df8b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f7d930df940>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f7d930df9d0>",
+        "forward": "<function SACPolicy.forward at 0x7f7d930dfa60>",
+        "_predict": "<function SACPolicy._predict at 0x7f7d930dfaf0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f7d930dfb80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f7d930d7ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "log_std_init": 0.1955317469998743,
+        "use_sde": false
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152564712700,
+    "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:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAAJnPOI0up0JA+TmElBhv8j+bS+vIroXCP2dJbPZNwaM/RWwDpW6O/L/Dv7IbjnTSP5+wkkdlBuC/UxjW/P+2lD/A93pIs9bBv+tmAbbFxg5AQhoV2cW92T+ei+cbuWIawMF+4h13tfC/Q4lnWOxnI8DFcT6kW48LQAAAAAAAACTAHPD28MrDnz8mc7EA6AYhwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "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": 999000,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "bounded_below": "[False False False False False False False False False False False False\n False False 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]",
+        "_shape": [
+            18
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf 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:": "gAWVeAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBgAAAAAAAAABAQEBAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBAolgYAAAAAAAAAAQEBAQEBlGgUSwaFlGgYdJRSlIwGX3NoYXBllEsGhZSMA2xvd5RoECiWGAAAAAAAAAAAAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaApLBoWUaBh0lFKUjARoaWdolGgQKJYYAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5RoCksGhZRoGHSUUpSMCGxvd19yZXBylIwELTEuMJSMCWhpZ2hfcmVwcpSMAzEuMJSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lGgxjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIaUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGg8ihDjYZWmt15YCS1Fllk0taEajANpbmOUihCpc3hEvDOBWIIa9zrb2o1BdYwKaGFzX3VpbnQzMpRLAIwIdWludGVnZXKUSwB1YnViLg==",
+        "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": 128,
+    "learning_starts": 1000,
+    "tau": 0.02,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "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 0x7f7d9312d700>",
+        "add": "<function ReplayBuffer.add at 0x7f7d9312d790>",
+        "sample": "<function ReplayBuffer.sample at 0x7f7d9312d820>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f7d9312d8b0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f7d931267c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f7d931267e0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

sac-seals-Walker2d-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc057da7f11966f0ddfd1f4d288815d37c819810470386fd82a97da2524da90
+size 1507

sac-seals-Walker2d-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9926991710dc6f599d2fb7ebbb88605192dddc4ce10a4ae0e636df275be009cd
+size 2625861

sac-seals-Walker2d-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba2f5a09d8b56f68285353b61133203b31cfa7108beca0f88cd4744e563e629
+size 747

sac-seals-Walker2d-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.2.0a3
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e496d6db563855be76482c16767e7e3e181f808bbe42f3b8725d12f3cd82d18
+size 31071