Initial commit

.gitattributes

@@ -29,3 +29,4 @@ 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 +1,65 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Swimmer-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 35.88 +/- 2.02
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Swimmer-v0
+      type: seals/Swimmer-v0
+---
+
+# **SAC** Agent playing **seals/Swimmer-v0**
+This is a trained model of a **SAC** agent playing **seals/Swimmer-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 seals/Swimmer-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo sac --env seals/Swimmer-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env seals/Swimmer-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env seals/Swimmer-v0 -f logs/ -orga HumanCompatibleAI
+```
+
+## 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',
+              'dict(net_arch=[400, 300], log_std_init=-2.689958330139309)'),
+             ('tau', 0.01),
+             ('train_freq', 256),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - device
+    - cpu
+  - - env
+    - seals/Swimmer-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - seals_experts_wandb_oldpickle/seed_5/
+  - - 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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 5
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/seals/Swimmer-v0__sac__5__1658841516
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - seals-experts-oldpickle

config.yml

@@ -0,0 +1,21 @@
+!!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
+    - dict(net_arch=[400, 300], log_std_init=-2.689958330139309)
+  - - tau
+    - 0.01
+  - - train_freq
+    - 256

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2734d573e8abd0607cda70ce0e28a83ea8d3cd561747a1d58a55d791ee947f2f
+size 425474

results.json

@@ -0,0 +1 @@
+{"mean_reward": 35.87843099999999, "std_reward": 2.0229172814859733, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-27T17:13:28.059429"}

sac-seals-Swimmer-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c273458046da9d86b10ebe901f57ccb4a12d31f64019cab1b177f94f08b4ab45
+size 5585012

sac-seals-Swimmer-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

sac-seals-Swimmer-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc3ff9ce8d770eec19b754546ae239d876736d80282c894436a658ae0892643
+size 1013341

sac-seals-Swimmer-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30116f753680549c64eb86f0d60e497bc07d4562924acd054cb97fabae90a91b
+size 2021689

sac-seals-Swimmer-v0/data

@@ -0,0 +1,120 @@
+{
+    "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 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 0x7f564e7b30d0>",
+        "_build": "<function SACPolicy._build at 0x7f564e7b3160>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f564e7b31f0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f564e7b3280>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f564e7b3310>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f564e7b33a0>",
+        "forward": "<function SACPolicy.forward at 0x7f564e7b3430>",
+        "_predict": "<function SACPolicy._predict at 0x7f564e7b34c0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f564e7b3550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f564e7ac900>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "log_std_init": -2.689958330139309,
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            10
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000192,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1658841519.201683,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVhQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFUvaG9tZS9tYXhpbWlsaWFuLy5sb2NhbC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgNdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzoz1Xjblu+FlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "tensorboard_log": "runs/seals/Swimmer-v0__sac__5__1658841516/seals-Swimmer-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:": "gAWVxQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAAAzeFosSrvI/3Yp3eVGt5L+GPu9/vlgCQKhBNLFnmvu/6wPaxNSD+7+0/s6pEFbIv8xzcGIBHqU/gHQvu2XydT88weFLL27PP3Q0cGlzTPG/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwqGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00019199999999996997,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 3904,
+    "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:\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 0x7f564e801280>",
+        "add": "<function ReplayBuffer.add at 0x7f564e801310>",
+        "sample": "<function ReplayBuffer.sample at 0x7f564e8013a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f564e801430>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f564e885480>"
+    },
+    "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
+}

sac-seals-Swimmer-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b076540a1a06d010cdeda76e163061ef7c0b0fccdb90b7ad9311d3c7230bff0
+size 1443

sac-seals-Swimmer-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853d85c160cf9fdc7845939655fc1d9fab3ef3eeeaae8cd6fac1138f8108473a
+size 2526661

sac-seals-Swimmer-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3564a08058b7e6be7a537fdbf0ef57f49a1fcfa7e3db43eeeda63b04850c4e87
+size 747

sac-seals-Swimmer-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-122-generic-x86_64-with-glibc2.29 #138-Ubuntu SMP Wed Jun 22 15:00:31 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.6.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: False
+Numpy: 1.22.3
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd915387091e2e422f675903fa744991d90b1face2dbeda9d8dcf9ca2047aeed
+size 31487