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/Hopper-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Hopper-v1
+      type: seals/Hopper-v1
+    metrics:
+    - type: mean_reward
+      value: 2279.30 +/- 124.09
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **seals/Hopper-v1**
+This is a trained model of a **SAC** agent playing **seals/Hopper-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/Hopper-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Hopper-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/Hopper-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo sac --env seals/Hopper-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env seals/Hopper-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env seals/Hopper-v1 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('buffer_size', 100000),
+             ('gamma', 0.98),
+             ('learning_rate', 0.001709807687567946),
+             ('learning_starts', 1000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'log_std_init': -1.6829391077276037,
+               'net_arch': [256, 256],
+               'use_sde': False}),
+             ('tau', 0.08),
+             ('train_freq', 32),
+             ('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/Hopper-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
+    - 1098537867
+  - - 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
+    - 0.98
+  - - learning_rate
+    - 0.001709807687567946
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - log_std_init: -1.6829391077276037
+      net_arch:
+      - 256
+      - 256
+      use_sde: false
+  - - tau
+    - 0.08
+  - - train_freq
+    - 32

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:bcb43a20b57c7eb1215bf45e7495ae2e8f36215890f5d67feb92cab4851820c4
+size 1330807

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2279.2973859, "std_reward": 124.08594365174518, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:51:44.999911"}

sac-seals-Hopper-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6ad7f94a3baab30637b53a6997e773bb6d8521c26ebca0b2ddc448a53d54fd
+size 3137779

sac-seals-Hopper-v1/_stable_baselines3_version

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfeb91a2497b2c253982d9b7e50e75d36d553d9016c62d9724401fdb3daed35b
+size 571549

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f415ff7285f0c86d4328f459a1ed0b09720c040e8f7ee5ec3aeaa6bfa9ba99
+size 1131513

sac-seals-Hopper-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 0x7faeb6b63700>",
+        "_build": "<function SACPolicy._build at 0x7faeb6b63790>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7faeb6b63820>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7faeb6b638b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7faeb6b63940>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7faeb6b639d0>",
+        "forward": "<function SACPolicy.forward at 0x7faeb6b63a60>",
+        "_predict": "<function SACPolicy._predict at 0x7faeb6b63af0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7faeb6b63b80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7faeb6b5ab10>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ],
+        "log_std_init": -1.6829391077276037,
+        "use_sde": false
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152489705476,
+    "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:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAEp1+0gm/jBA2MNKBLYOzj8lzH34uXn5P8K1maCoEoQ/XuYPcaIdkz8nD9So45bjP7zyd9ELWQJAZdIPWumQ9L/dhjXUK8vzPy7jaDlrEfO/2H/tgwAj8L96v7b7wnoZwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsMhpSMAUOUdJRSlC4="
+    },
+    "_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": 31219,
+    "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]",
+        "bounded_above": "[False False False False False False False False False False False False]",
+        "_shape": [
+            12
+        ],
+        "low": "[-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]",
+        "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]",
+        "bounded_above": "[ True  True  True]",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[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": 0.08,
+    "gamma": 0.98,
+    "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 0x7faeb6bb0700>",
+        "add": "<function ReplayBuffer.add at 0x7faeb6bb0790>",
+        "sample": "<function ReplayBuffer.sample at 0x7faeb6bb0820>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7faeb6bb08b0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7faeb6ba9820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7faeb6ba9840>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLIGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "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-Hopper-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e52c96a4af45683911d24cca80f86084bb7c8de294de38418e1ea5054fc0c4
+size 1507

sac-seals-Hopper-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2750fe958fdec1e32cc809e8200420e969276031a9daf3709f78191e274e5f47
+size 1415493

sac-seals-Hopper-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ea903b7595ed50bb0054345f5675de8ca82cf2d04e80da46afc921b8427126
+size 747

sac-seals-Hopper-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 sha256:818601e1f03a8d87ec73733cbbd3f72fe57badff12dbcbf1f3f42aa879747d55
+size 29672