Initial Commit

.gitattributes

@@ -25,3 +25,4 @@ 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 +1,61 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 91.17 +/- 0.26
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+---
+
+# **A2C** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **A2C** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo a2c --env MountainCarContinuous-v0 -orga sb3 -f logs/
+python enjoy --algo a2c --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo a2c --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo a2c --env MountainCarContinuous-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('n_envs', 4),
+             ('n_steps', 100),
+             ('n_timesteps', 100000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=0.0, ortho_init=False)'),
+             ('sde_sample_freq', 16),
+             ('use_sde', True),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

a2c-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf290ba95f19c5e4fc1e8e1b0929a97e6c140a45012b7065739ddbc92bf7630
+size 95974

a2c-MountainCarContinuous-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a6

a2c-MountainCarContinuous-v0/data

@@ -0,0 +1,103 @@
+{
+    "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 0x7feb3acb1cb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7feb3acb1d40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7feb3acb1dd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7feb3acb1e60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7feb3acb1ef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7feb3acb1f80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7feb3acb8050>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7feb3acb80e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7feb3acb8170>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7feb3acb8200>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7feb3acb8290>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7feb3ad046f0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVpwAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRHAAAAAAAAAACMCm9ydGhvX2luaXSUiYwPb3B0aW1pemVyX2NsYXNzlIwTdG9yY2gub3B0aW0ucm1zcHJvcJSMB1JNU3Byb3CUk5SMEG9wdGltaXplcl9rd2FyZ3OUfZQojAVhbHBoYZRHP++uFHrhR66MA2Vwc5RHPuT4tYjjaPGMDHdlaWdodF9kZWNheZRLAHV1Lg==",
+        "log_std_init": 0.0,
+        "ortho_init": false,
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAJqZmb8pXI+9lGgKSwKFlIwBQ5R0lFKUjARoaWdolGgQKJYIAAAAAAAAAJqZGT8pXI89lGgKSwKFlGgTdJRSlIwNYm91bmRlZF9iZWxvd5RoECiWAgAAAAAAAAABAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZRoE3SUUpSMDWJvdW5kZWRfYWJvdmWUaBAolgIAAAAAAAAAAQGUaB9LAoWUaBN0lFKUjApfbnBfcmFuZG9tlE6MBl9zaGFwZZRLAoWUdWIu",
+        "dtype": "float32",
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null,
+        "_shape": [
+            2
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            1
+        ]
+    },
+    "n_envs": 4,
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614619328.9998071,
+    "learning_rate": 0.0007,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOvH774AAAAAajUNvwAAAABGTBi/AAAAAEwR6b4AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": 16,
+    "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 250,
+    "n_steps": 100,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    }
+}

a2c-MountainCarContinuous-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2251026211973dbbc37fbf69a03dd425e38913671959dc58d4eb53b25da4420
+size 39102

a2c-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5af105a9471b991f0d27d7cbc31f172a479aab93e509a01a360228ffa93aec
+size 39742

a2c-MountainCarContinuous-v0/pytorch_variables.pth

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

a2c-MountainCarContinuous-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-110-generic-x86_64-with-debian-bullseye-sid #124-Ubuntu SMP Thu Apr 14 19:46:19 UTC 2022
+Python: 3.7.12
+Stable-Baselines3: 1.5.1a6
+PyTorch: 1.11.0+cpu
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - env
+    - MountainCarContinuous-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 958554542
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,19 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - n_envs
+    - 4
+  - - n_steps
+    - 100
+  - - n_timesteps
+    - 100000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=0.0, ortho_init=False)
+  - - sde_sample_freq
+    - 16
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6747635d27e483256e02bb53fd8a63dac98889af0312b9f013a5568d5465bb48
+size 257975

results.json

@@ -0,0 +1 @@
+{"mean_reward": 91.16943280000001, "std_reward": 0.2582569216802508, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T09:34:46.401860"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27de6fa6ab8dab9e983e9e63e53603ff06fd02dcf74103dfeb7fc94f178d17a
+size 22034