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 +1,79 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Swimmer-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Swimmer-v1
+      type: seals/Swimmer-v1
+    metrics:
+    - type: mean_reward
+      value: 28.90 +/- 1.67
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **seals/Swimmer-v1**
+This is a trained model of a **SAC** agent playing **seals/Swimmer-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/Swimmer-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Swimmer-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/Swimmer-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Swimmer-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env seals/Swimmer-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env seals/Swimmer-v1 -f logs/ -orga ernestum
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 100000),
+             ('gamma', 0.995),
+             ('learning_rate', 0.00039981805535514633),
+             ('learning_starts', 1000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'log_std_init': -2.689958330139309,
+               'net_arch': [400, 300],
+               'use_sde': False}),
+             ('tau', 0.01),
+             ('train_freq', 256),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - hyperparams/python/sac.py
+  - - device
+    - cpu
+  - - env
+    - seals/Swimmer-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
+    - 3450306094
+  - - 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
+    - 0.995
+  - - learning_rate
+    - 0.00039981805535514633
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - log_std_init: -2.689958330139309
+      net_arch:
+      - 400
+      - 300
+      use_sde: false
+  - - tau
+    - 0.01
+  - - train_freq
+    - 256

env_kwargs.yml

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

results.json

@@ -0,0 +1 @@
+{"mean_reward": 28.9023299, "std_reward": 1.6711585563886182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:55:41.749317"}

sac-seals-Swimmer-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c995510e331e9b3b1660f1e4df2df5e89512b21af0c698b852460bceb9d07e6
+size 5580789

sac-seals-Swimmer-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716c0ebc3d6687f9cc18cac17b2f11d175a53909dcad32e42ed8d6daf852c65c
+size 1013341

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473b30242d77fbaa85e3797c9de06d5e0bb285901df466f8f69671dcd0450354
+size 2021689

sac-seals-Swimmer-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 0x7f739ad838b0>",
+        "_build": "<function SACPolicy._build at 0x7f739ad83940>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f739ad839d0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f739ad83a60>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f739ad83af0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f739ad83b80>",
+        "forward": "<function SACPolicy.forward at 0x7f739ad83c10>",
+        "_predict": "<function SACPolicy._predict at 0x7f739ad83ca0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f739ad83d30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f739ad84870>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "log_std_init": -2.689958330139309,
+        "use_sde": false
+    },
+    "num_timesteps": 1000192,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152591166862,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzoz1Xjblu+FlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "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:": "gAWVxQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAAPglUX4fOfQ/v4z3FTJ65D+rQaBeSPMCwOihJP/B7/o/fXe6Mvzt+T8sg72TRe3mv+ofXhCAPtY/ZeKV/L397z/4R/DzoW34vyPyUOZOavI/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwqGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00019199999999996997,
+    "_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": 3904,
+    "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]",
+        "bounded_above": "[False False False False False False False False False False]",
+        "_shape": [
+            10
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[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]",
+        "bounded_above": "[ True  True]",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[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": 0.01,
+    "gamma": 0.995,
+    "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 0x7f739ad4d820>",
+        "add": "<function ReplayBuffer.add at 0x7f739ad4d8b0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f739ad4d940>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f739ad4d9d0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f739ad53580>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f739ad535a0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -2.0,
+    "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-Swimmer-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dce96ec0543c74863ec1698452dd9a3664c37427a8b0d828bd070cc2752c509
+size 1507

sac-seals-Swimmer-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a05ebd00d8f98d1a432cb953b2faabec55dfcd12dbb82f170d138bbda0bfd1b
+size 2526661

sac-seals-Swimmer-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f59fff7ad49cf0265cde03fb19a50f58219fc864508fbb80b2cec564b0b078d
+size 747

sac-seals-Swimmer-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: 2.1.0
+- 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 sha256:2fd65d60136370c24d24b1bbdd4d9b6ea00503f6a2dc4bb79758537234f8795e
+size 27986