Initial commit

.gitattributes

@@ -29,3 +29,4 @@ 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: -336.60 +/- 406.53
+      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 HumanCompatibleAI -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 HumanCompatibleAI
+```
+
+## 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
+    - rl-trained-agents
+  - - 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
+    - 1867484813
+  - - 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:c4bd693f82b9e4089d5ac764b148dad2e1410a01ebf2b4d8add2eff3e32db789
+size 139146

ppo-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

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 0x7f708aee2af0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f708aee2b80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f708aee2c10>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f708aee2ca0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f708aee2d30>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f708aee2dc0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f708aee2e50>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f708aee2ee0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f708aee2f70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f708aee6040>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f708aee60d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f708aee4090>"
+    },
+    "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": 1658759207.2481482,
+    "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 sha256:6268fddd3f5501ae4bd68c7da9e32a3cce8d0a80e3f360ba472a9b0bdfd91ae6
+size 78871

ppo-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b138cb692f3fddb67a0015036b3374d642f2744c1fc44d19776aa77b862ffec9
+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-5.4.0-122-generic-x86_64-with-glibc2.29 #138-Ubuntu SMP Wed Jun 22 15:00:31 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.6.0
+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:ea712fbe50a84013ce4e23f94663d59927551fa721c246294b3fdd38d49ad672
+size 138013

results.json

@@ -0,0 +1 @@
+{"mean_reward": -336.60077279999996, "std_reward": 406.5254085374081, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T16:30:45.639168"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66775a65923ae2f631af7881b6b21f958ac3e55dde12361d15848ccda69f0ec
+size 15547