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/MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -101.70 +/- 6.18
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/MountainCar-v0
+      type: seals/MountainCar-v0
+---
+
+# **PPO** Agent playing **seals/MountainCar-v0**
+This is a trained model of a **PPO** agent playing **seals/MountainCar-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/MountainCar-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo ppo --env seals/MountainCar-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env seals/MountainCar-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env seals/MountainCar-v0 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('clip_range', 0.2),
+             ('ent_coef', 6.4940755116195606e-06),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.99),
+             ('learning_rate', 0.0004476103728105138),
+             ('max_grad_norm', 1),
+             ('n_envs', 16),
+             ('n_epochs', 20),
+             ('n_steps', 256),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              'dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, '
+              '64])])'),
+             ('vf_coef', 0.25988158989488963),
+             ('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/MountainCar-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
+    - 4
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/seals/MountainCar-v0__ppo__4__1658498360
+  - - 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
+    - 0.2
+  - - ent_coef
+    - 6.4940755116195606e-06
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - 0.0004476103728105138
+  - - max_grad_norm
+    - 1
+  - - n_envs
+    - 16
+  - - n_epochs
+    - 20
+  - - n_steps
+    - 256
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  - - vf_coef
+    - 0.25988158989488963

env_kwargs.yml

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

ppo-seals-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cda518a8633bbeb6dd174bc61f827a298d8d556853e7414ac9f6764b66d77c7
+size 139525

ppo-seals-MountainCar-v0/_stable_baselines3_version

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

ppo-seals-MountainCar-v0/data

@@ -0,0 +1,113 @@
+{
+    "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 0x7ffb1bac5790>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffb1bac5820>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffb1bac58b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffb1bac5940>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ffb1bac59d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ffb1bac5a60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffb1bac5af0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ffb1bac5b80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffb1bac5c10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffb1bac5ca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffb1bac5d30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7ffb1babbcc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVaAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWF1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
+        "net_arch": [
+            {
+                "pi": [
+                    64,
+                    64
+                ],
+                "vf": [
+                    64,
+                    64
+                ]
+            }
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 16,
+    "num_timesteps": 1003520,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1658498364.7560694,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/seals/MountainCar-v0__ppo__4__1658498360/seals-MountainCar-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAB7z5b4AAAAAyykTvwAAAADv6Ae/AAAAACWCC78AAAAAWPLvvgAAAACS0gK/AAAAAGl+9r4AAAAAYqkAvwAAAAALSQS/AAAAANWE7b4AAAAAo+gTvwAAAABIX9++AAAAAE8Pzr4AAAAATGXqvgAAAADavQ+/AAAAAGkJ8r4AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4900,
+    "n_steps": 256,
+    "gamma": 0.99,
+    "gae_lambda": 0.98,
+    "ent_coef": 6.4940755116195606e-06,
+    "vf_coef": 0.25988158989488963,
+    "max_grad_norm": 1,
+    "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-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90156d9bca35512749633228d33cf2026e4e7b75e7ed0b73b474d107249da25c
+size 80889

ppo-seals-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe77da1a5391bea6f0eb612b8ae3114c6a2e37391c7c000a96b6c4d81eaa8eee
+size 39745

ppo-seals-MountainCar-v0/pytorch_variables.pth

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

ppo-seals-MountainCar-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 sha256:1d77cb16b441d277b0ec5dd77e689043cde287194c94f7521b71d3a5d4bdce88
+size 158178

results.json

@@ -0,0 +1 @@
+{"mean_reward": -101.7, "std_reward": 6.181423784210236, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T13:00:27.015059"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76259ab9d9e40f8a57cfa256fbb9fbfa90d3beb3ea45d842ae90efa27a7315d8
+size 119963

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09736caaa11fa6d590e207260a1c4cc66b041366413d470ba377b9a2c8d35630
+size 4136