Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -109.40 +/- 8.96
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **MountainCar-v0**
+This is a trained model of a **PPO** agent playing **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 rl_zoo3.load_from_hub --algo ppo --env MountainCar-v0 -orga RayanRen -f logs/
+python enjoy.py --algo ppo --env MountainCar-v0  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo ppo --env MountainCar-v0 -orga RayanRen -f logs/
+rl_zoo3 enjoy --algo ppo --env MountainCar-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env MountainCar-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env MountainCar-v0 -f logs/ -orga RayanRen
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.99),
+             ('n_envs', 16),
+             ('n_epochs', 4),
+             ('n_steps', 16),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - MountainCar-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs/
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2430380512
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,19 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.99
+  - - n_envs
+    - 16
+  - - n_epochs
+    - 4
+  - - n_steps
+    - 16
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd2603deb019d304264ad7ee759d2977c1118bbda72bff535f024770b06114c
+size 138668

ppo-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-MountainCar-v0/data

@@ -0,0 +1,94 @@
+{
+    "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 0x000001C83323A160>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001C83323A1F0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001C83323A280>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001C83323A310>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001C83323A3A0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001C83323A430>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001C83323A4C0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001C83323A550>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001C83323A5E0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001C83323A670>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001C83323A700>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x000001C833230F30>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "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": 1,
+    "num_timesteps": 980864,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1672234840258174300,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAACBJ174AAAAABZYOvwAAAAAuvA2/AAAAAIMPCL8AAAAAnhEGvwAAAAB8cBK/AAAAAE1+D78AAAAAJrT0vgAAAAA+7uK+AAAAAKJc874AAAAAJnDlvgAAAACe+c2+AAAAAEl/Ab8AAAAAPaPTvgAAAADht/G+AAAAANcNEr8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.019263999999999948,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 15324,
+    "n_steps": 16,
+    "gamma": 0.99,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6694d02a561a9f51348b9cb30603cb6026d05182d0ce4f81eb8a8fb0e94de264
+size 81401

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6460dca8a848030afc2034b1032c6f5107941a57939557b8d03f20f2d2f9fd3
+size 39873

ppo-MountainCar-v0/pytorch_variables.pth

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

ppo-MountainCar-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Windows-10-10.0.22621-SP0 10.0.22621
+Python: 3.8.0
+Stable-Baselines3: 1.6.2
+PyTorch: 1.13.1+cu116
+GPU Enabled: True
+Numpy: 1.24.0
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -109.4, "std_reward": 8.957678270623477, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-28T20:51:40.432935"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff60d4e70080d6da7913ef7721144dc01c1e09f8c717e4672c3193cca5e12eac
+size 190129

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209d662e757320282ccbbc3522182287b49205907955d7ead34f372249b1db53
+size 4171