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 +1,78 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -189.25 +/- 66.36
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+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 Pendulum-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env Pendulum-v1  -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 Pendulum-v1 -orga ernestum -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env Pendulum-v1 -f logs/ -orga ernestum
+```
+
+## 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 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - cpu
+  - - env
+    - Pendulum-v1
+  - - 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
+    - 3755125310
+  - - 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 +1,25 @@
+!!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:aa88fec6c8ad62de18627fac90373e1cb1f7005da2df367889e90b851c66aa1c
+size 137828

ppo-Pendulum-v1/_stable_baselines3_version

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

ppo-Pendulum-v1/data

@@ -0,0 +1,105 @@
+{
+    "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 0x7fd294b67040>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd294b670d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd294b67160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd294b671f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fd294b67280>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fd294b67310>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd294b673a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd294b67430>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fd294b674c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd294b67550>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd294b675e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd294b67670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fd294b42ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 102400,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694771152245526076,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_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,
+    "_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": 250,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "low_repr": "[-1. -1. -8.]",
+        "high_repr": "[1. 1. 8.]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "low_repr": "-2.0",
+        "high_repr": "2.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL21heGltaWxpYW4vcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1BiTdLxqfyFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    }
+}

ppo-Pendulum-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a97ba3110e2c7500d7371d0b6d4cae11d9458e713b3558c89bf99b2f55872b
+size 82160

ppo-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be542f8bb454365173f9e4ea14ab68cabc11b968254a49fb0dbad55bed400c16
+size 40382

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 +1,9 @@
+- 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": -189.2534682, "std_reward": 66.36133815611241, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:52:49.960932"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ce2124af89a6fc975e8699dd5cfc9103572037576aa9591d9f0cb6038a2d22
+size 15240