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/Walker2d-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 5483.53 +/- 1474.79
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Walker2d-v0
+      type: seals/Walker2d-v0
+---
+
+# **SAC** Agent playing **seals/Walker2d-v0**
+This is a trained model of a **SAC** agent playing **seals/Walker2d-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/Walker2d-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo sac --env seals/Walker2d-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env seals/Walker2d-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env seals/Walker2d-v0 -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',
+              'dict(net_arch=[400, 300], log_std_init=0.1955317469998743)'),
+             ('tau', 0.02),
+             ('train_freq', 1),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - device
+    - cpu
+  - - env
+    - seals/Walker2d-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - seals_experts_wandb_oldpickle/seed_9/
+  - - 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
+    - 9
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/seals/Walker2d-v0__sac__9__1658867336
+  - - 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
+    - 0.99
+  - - learning_rate
+    - 0.0005845844772048097
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300], log_std_init=0.1955317469998743)
+  - - tau
+    - 0.02
+  - - train_freq
+    - 1

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25270b7045ff6072b4ae60879bc63412b8e64456209e33f512817f1b0868bb37
+size 1514202

results.json

@@ -0,0 +1 @@
+{"mean_reward": 5483.5284099, "std_reward": 1474.7914335759533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-27T17:07:09.427002"}

sac-seals-Walker2d-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9712739c0b31fa0ded5734064e57bb93cf474fdfe1c2e12285320e44f1827b35
+size 5806370

sac-seals-Walker2d-v0/_stable_baselines3_version

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

sac-seals-Walker2d-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5bc4b1a434075dbc54e465412dd6806ba1813b0a394785f158cdaf78639c1c
+size 1058141

sac-seals-Walker2d-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7e185fe43419961da95f886d57e530dbef3a774b46bb64e99f652f5c4f0cc2
+size 2098489

sac-seals-Walker2d-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 0x7fc91ed020d0>",
+        "_build": "<function SACPolicy._build at 0x7fc91ed02160>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fc91ed021f0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fc91ed02280>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fc91ed02310>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fc91ed023a0>",
+        "forward": "<function SACPolicy.forward at 0x7fc91ed02430>",
+        "_predict": "<function SACPolicy._predict at 0x7fc91ed024c0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fc91ed02550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc91ecfa900>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "log_std_init": 0.1955317469998743,
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_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]",
+        "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]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1658867341.4222457,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/seals/Walker2d-v0__sac__9__1658867336/seals-Walker2d-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:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAAGqDd90TvkJAZpNNisRh8D9Y6zSr4uLtv+ydyoLb9f6/KSTfivXKkb+QmHue3BDnv3YiEguUnnO/h/lNChsXA8Akc1zZzizqP0OhVSIAARdAXMGsJM9x7j/VepoCGRoWQFQL1ROz8BpAtMbeFhSFFcAAAAAAAAAkQDXEYbnQkhJAgA4whY+tDEAbrivXzDqmv5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 999000,
+    "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:\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 0x7fc91ed4f280>",
+        "add": "<function ReplayBuffer.add at 0x7fc91ed4f310>",
+        "sample": "<function ReplayBuffer.sample at 0x7fc91ed4f3a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc91ed4f430>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc91edd4480>"
+    },
+    "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
+}

sac-seals-Walker2d-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f1de550e86e01b6bb196030381f7d8f2a07e4528bff5ded6124a75ad19407b
+size 1443

sac-seals-Walker2d-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728488ceeaf8e8a938a6b8a09633b86c78ad8d2ca8393bece3f07513f6c172a
+size 2625861

sac-seals-Walker2d-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0454ce24fe9e06e273157d4b0eef01ca0d87fde278d816d6f962b224f6c84262
+size 747

sac-seals-Walker2d-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 sha256:32a770dcf146bfd5619996c4df4100ed7f9044ea3d78f4bbc627f664fce45300
+size 34693