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 +1,71 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Hopper-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 3416.00 +/- 328.59
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Hopper-v0
+      type: seals/Hopper-v0
+---
+
+# **PPO** Agent playing **seals/Hopper-v0**
+This is a trained model of a **PPO** 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 ppo --env seals/Hopper-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo ppo --env seals/Hopper-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env seals/Hopper-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env seals/Hopper-v0 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('clip_range', 0.1),
+             ('ent_coef', 0.0010159833764878474),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.995),
+             ('learning_rate', 0.0003904770450788824),
+             ('max_grad_norm', 0.9),
+             ('n_envs', 1),
+             ('n_epochs', 20),
+             ('n_steps', 2048),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              'dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, '
+              '64])])'),
+             ('vf_coef', 0.20315938606555833),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - 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/
+  - - 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
+    - 3
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/seals/Hopper-v0__ppo__3__1658506790
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - seals-experts

config.yml

@@ -0,0 +1,31 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - clip_range
+    - 0.1
+  - - ent_coef
+    - 0.0010159833764878474
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.995
+  - - learning_rate
+    - 0.0003904770450788824
+  - - max_grad_norm
+    - 0.9
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 20
+  - - n_steps
+    - 2048
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(activation_fn=nn.ReLU, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  - - vf_coef
+    - 0.20315938606555833

env_kwargs.yml

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

ppo-seals-Hopper-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a407322ebbe5379da993298470dc40ca9509a76b234922cc807e26a7f4dcf00
+size 158297

ppo-seals-Hopper-v0/_stable_baselines3_version

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

ppo-seals-Hopper-v0/data

@@ -0,0 +1,118 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\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()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f83f9848790>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f83f9848820>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f83f98488b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f83f9848940>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f83f98489d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f83f9848a60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f83f9848af0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f83f9848b80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f83f9848c10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f83f9848ca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f83f9848d30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f83f983ecc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVaAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWF1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            {
+                "pi": [
+                    64,
+                    64
+                ],
+                "vf": [
+                    64,
+                    64
+                ]
+            }
+        ]
+    },
+    "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": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1658506793.6917925,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/seals/Hopper-v0__ppo__3__1658506790/seals-Hopper-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAMzEUlAWsGI/tPAnR9z18z8AJT2MX+RiP2bLA9WR+WA/lD0frGfOVD/4JM4FzwhDv3FdG5QtomW/yh6CLn1Kab/K9BHXB7JkP/DFJmBsu1y/gmbP62ZIaz8TMqG1iVxyv5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsMhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0014719999999999178,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 9780,
+    "n_steps": 2048,
+    "gamma": 0.995,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.0010159833764878474,
+    "vf_coef": 0.20315938606555833,
+    "max_grad_norm": 0.9,
+    "batch_size": 512,
+    "n_epochs": 20,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-seals-Hopper-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd298eb508dac86e144c8988cf2d578b0c10df58cd305762032bf044dc960b6
+size 91824

ppo-seals-Hopper-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9422974a7f5c84ad8f96bc23910b78a368f1b904f2d63b79402f0578c59ad05d
+size 45182

ppo-seals-Hopper-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dafde268c02213d02b86cac800368c0ba6e6c377b40c1dbaea1a2b978cea6fe
+size 1671968

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3416.0004174, "std_reward": 328.5927750661263, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T13:07:30.216833"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e6b2c0151615cf838ebed817c01d8968ebb1887a5b6546ffb4bc48e559a143
+size 33659

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed42710d7b2cfb19f78f0315fb13b9fa9ef073315ae8d57f03ce85689b1e47e0
+size 4488