Initial commit

.gitattributes

@@ -25,3 +25,5 @@ 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
+vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 87.80 +/- 0.28
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+---
+
+# **PPO** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **PPO** agent playing **MountainCarContinuous-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 MountainCarContinuous-v0 -orga danieladejumo -f logs/
+python enjoy.py --algo ppo --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env MountainCarContinuous-v0 -f logs/ -orga danieladejumo
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 0.1),
+             ('ent_coef', 0.00429),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.9999),
+             ('learning_rate', 7.77e-05),
+             ('max_grad_norm', 5),
+             ('n_envs', 1),
+             ('n_epochs', 10),
+             ('n_steps', 8),
+             ('n_timesteps', 20000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3.29, ortho_init=False)'),
+             ('use_sde', True),
+             ('vf_coef', 0.19),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - MountainCarContinuous-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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2769432491
+  - - 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

config.yml

@@ -0,0 +1,33 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - 0.1
+  - - ent_coef
+    - 0.00429
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.9999
+  - - learning_rate
+    - 7.77e-05
+  - - max_grad_norm
+    - 5
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 8
+  - - n_timesteps
+    - 20000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3.29, ortho_init=False)
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.19

env_kwargs.yml

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

ppo-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6487088e648591b4b79056855d2420c9729c0d10998542e313c3b10b21444e3
+size 136888

ppo-MountainCarContinuous-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

ppo-MountainCarContinuous-v0/data

@@ -0,0 +1,105 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7f7b239ff8c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7b239ff950>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7b239ff9e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7b239ffa70>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f7b239ffb00>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f7b239ffb90>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7b239ffc20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f7b239ffcb0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7b239ffd40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7b239ffdd0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7b239ffe60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f7b239d29c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3.29,
+        "ortho_init": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "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.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1656623259.1174614,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVkgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMIr58AvwAAAACUdJRiLg=="
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 25000,
+    "n_steps": 8,
+    "gamma": 0.9999,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.00429,
+    "vf_coef": 0.19,
+    "max_grad_norm": 5,
+    "batch_size": 256,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCarContinuous-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93da08ec99a6033f9d142334d3b4a00337ddc586abef0f2af63598095509b29
+size 78167

ppo-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786a24d2577a2556ebd10e9ed9588b3f7613579fe10edae32d0288db3e694785
+size 39870

ppo-MountainCarContinuous-v0/pytorch_variables.pth

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

ppo-MountainCarContinuous-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc977b46180817c5a3d3a2431fb536172fea07b78fa8614402286b224b920675
+size 242189

results.json

@@ -0,0 +1 @@
+{"mean_reward": 87.804662, "std_reward": 0.2817113585519775, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-30T21:12:02.534900"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45e6b9c687f399dfaf1ee1d0fc3ceb38bbb127c995508c3280008e11ad08e0d
+size 3611

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4016cc9061d49c349aee8f68206e63f4f21f1bde0ed4a4b310f384ce6ade630c
+size 4305