Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,89 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/MountainCar-v0
+      type: seals/MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -97.00 +/- 8.26
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/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 seals/MountainCar-v0 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/MountainCar-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env seals/MountainCar-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env seals/MountainCar-v0 -f logs/ -orga ernestum
+```
+
+## 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',
+              {'gamma': 0.99, 'norm_obs': False, 'norm_reward': True}),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,
+               'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
+               'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
+             ('vf_coef', 0.25988158989488963),
+             ('normalize_kwargs',
+              {'norm_obs': {'gamma': 0.99,
+                            'norm_obs': False,
+                            'norm_reward': True},
+               'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - hyperparams/python/ppo.py
+  - - device
+    - cpu
+  - - env
+    - seals/MountainCar-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - 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
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 392828721
+  - - 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
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,41 @@
+!!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
+    - gamma: 0.99
+      norm_obs: false
+      norm_reward: true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - activation_fn: !!python/name:torch.nn.modules.activation.Tanh ''
+      features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
+      net_arch:
+      - 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:eeafa5a1bbde997865f4caf9a026492406ba2c7d94c474013e232411d622c8ab
+size 138501

ppo-seals-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

ppo-seals-MountainCar-v0/data

@@ -0,0 +1,117 @@
+{
+    "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f184ff7a040>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f184ff7a0d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f184ff7a160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f184ff7a1f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f184ff7a280>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f184ff7a310>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f184ff7a3a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f184ff7a430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f184ff7a4c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f184ff7a550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f184ff7a5e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f184ff7a670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f184ff55ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVuQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXWMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        },
+        "features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
+    },
+    "num_timesteps": 1003520,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152324454564,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAHyIFb8AAAAAANsRvwAAAAAMG92+AAAAAAfI4r4AAAAAqWLhvgAAAAB2KRa/AAAAAGsdDL8AAAAAVwjavgAAAABhC/m+AAAAANRiCr8AAAAAqJ4QvwAAAADaLAi/AAAAAKofB78AAAAAxmMPvwAAAAA0Jem+AAAAAFRmCL8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4900,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "low_repr": "[-1.2  -0.07]",
+        "high_repr": "[0.6  0.07]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1c31ec7330c2541c0a041c35dbb6fabeaf54167bbb12708858af3318b003d8
+size 80889

ppo-seals-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db04f92e352505178fbc6e573fe383593c3755cbf7097e4ad8672c4c4e3ee434
+size 41528

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 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -97.0, "std_reward": 8.258329128825032, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:50:09.495577"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f676caa1f922426dddd659c6ed28ee065eb3800b0beb426ced4b03df62e4fb
+size 114460

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cf903957df5a7298c7c4285b9cfed43095dae50144cf1ef1a12c59f0947389
+size 1687