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/Hopper-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 2575.48 +/- 173.56
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Hopper-v0
+      type: seals/Hopper-v0
+---
+
+# **SAC** Agent playing **seals/Hopper-v0**
+This is a trained model of a **SAC** agent playing **seals/Hopper-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/Hopper-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo sac --env seals/Hopper-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env seals/Hopper-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env seals/Hopper-v0 -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',
+              'dict(net_arch=[256, 256], log_std_init=-1.6829391077276037)'),
+             ('tau', 0.08),
+             ('train_freq', 32),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - device
+    - cpu
+  - - env
+    - seals/Hopper-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/Hopper-v0__sac__9__1658846826
+  - - 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
+    - 0.98
+  - - learning_rate
+    - 0.001709807687567946
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256], log_std_init=-1.6829391077276037)
+  - - tau
+    - 0.08
+  - - train_freq
+    - 32

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66163d8265993c6bf0a9113cc119aac06b3c6219fd98fd8dd8361ac8f706291c
+size 1618352

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2575.4775179000003, "std_reward": 173.55675379625745, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-27T17:08:34.032151"}

sac-seals-Hopper-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661c86229f3fc3a2a8e845e385459119c0f39b5f01c1aeab3483fa3d9055c9b6
+size 3141993

sac-seals-Hopper-v0/_stable_baselines3_version

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156f64b0f29323597d99f522c38addc244a1dc9543b1f4c26e310c4078ed31fd
+size 571549

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4122376262604ba2c27998eba1edbe8292e90e23bc43d6829f2bcc71d0e728ba
+size 1131513

sac-seals-Hopper-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 0x7f2eeb6270d0>",
+        "_build": "<function SACPolicy._build at 0x7f2eeb627160>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f2eeb6271f0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f2eeb627280>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f2eeb627310>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f2eeb6273a0>",
+        "forward": "<function SACPolicy.forward at 0x7f2eeb627430>",
+        "_predict": "<function SACPolicy._predict at 0x7f2eeb6274c0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f2eeb627550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2eeb61f900>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ],
+        "log_std_init": -1.6829391077276037,
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_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]",
+        "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]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ 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": 1658846830.1354108,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/seals/Hopper-v0__sac__9__1658846826/seals-Hopper-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVhQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFUvaG9tZS9tYXhpbWlsaWFuLy5sb2NhbC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgNdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1wDdAZveNiFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAGZQFDBpIzJAJbceQdLhvj/TOzH2OLv5P2ZW3IvuEsK/tCz6S8OCk78QMFUaVMbOvwkJIyC3KghAZFY67mTA7D8+xMXbVsIUwKJW55wxHxXAsMyhI/E+nj8qoCIwRS0ewJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsMhpSMAUOUdJRSlC4="
+    },
+    "_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": 31219,
+    "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:\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 0x7f2eeb675280>",
+        "add": "<function ReplayBuffer.add at 0x7f2eeb675310>",
+        "sample": "<function ReplayBuffer.sample at 0x7f2eeb6753a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f2eeb675430>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2eeb6f9480>"
+    },
+    "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
+}

sac-seals-Hopper-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48e55dede4acbeb2915f62573714bdb546b242fc24c35d8538326c2c47f6239
+size 1443

sac-seals-Hopper-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd2ecaf1c6a849d1c90e4d3b1f7aa6eb8049ab005402a5c8f20e14cdfd7cbe8
+size 1415493

sac-seals-Hopper-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13128e55795707e8815425ba293f6027f66d1543c5518ac1ebe6b660a62750eb
+size 747

sac-seals-Hopper-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 sha256:683473fa51b476095adf0f0d0215333e004d9a92017df0d71f8fcde806d56cbc
+size 33513