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 +1,66 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -227.99 +/- 144.65
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+---
+
+# **PPO** Agent playing **Pendulum-v1**
+This is a trained model of a **PPO** agent playing **Pendulum-v1**
+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 Pendulum-v1 -orga ernestumorga -f logs/
+python enjoy.py --algo ppo --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env Pendulum-v1 -f logs/ -orga ernestumorga
+```
+
+## Hyperparameters
+```python
+OrderedDict([('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.9),
+             ('learning_rate', 0.001),
+             ('n_envs', 4),
+             ('n_epochs', 10),
+             ('n_steps', 1024),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - 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
+    - 1237341224
+  - - 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 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.9
+  - - learning_rate
+    - 0.001
+  - - n_envs
+    - 4
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true

env_kwargs.yml

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

ppo-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c6ce02dc14354d0712d08c591dd07d16573761d205e5544ca5008f7f976da3
+size 139136

ppo-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a7

ppo-Pendulum-v1/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7feca71cc0d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7feca71cc160>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7feca71cc1f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7feca71cc280>",
+        "_build": "<function ActorCriticPolicy._build at 0x7feca71cc310>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7feca71cc3a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7feca71cc430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7feca71cc4c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7feca71cc550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7feca71cc5e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7feca71cc670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7feca71c72a0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 4,
+    "num_timesteps": 102400,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1654610185.237497,
+    "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:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": 4,
+    "_current_progress_remaining": -0.02400000000000002,
+    "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": 1024,
+    "gamma": 0.9,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-Pendulum-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbf108a66febbfcfaca2939a22d5be9b2904856fa54c999df0dcf687357bddb
+size 78871

ppo-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f518a9755bc8822dcf657fe014e2d1d7ca1ab69889ffc871650b98b9e189a449
+size 40254

ppo-Pendulum-v1/pytorch_variables.pth

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

ppo-Pendulum-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-109-generic-x86_64-with-glibc2.29 #123-Ubuntu SMP Fri Apr 8 09:10:54 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.5.1a7
+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:fd6aba8777fe10bc86e6e1415cc66ff6417d15a19d866bbe218ede118e568965
+size 143419

results.json

@@ -0,0 +1 @@
+{"mean_reward": -227.99178550000002, "std_reward": 144.64611247723332, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-07T16:05:58.437311"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb5d0840d51a264fd8d7c3e6163223fe8fca9feefc0da60c70d0c246961fb5e
+size 15601