Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,80 @@
+---
+library_name: stable-baselines3
+tags:
+- InvertedDoublePendulum-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: InvertedDoublePendulum-v2
+      type: InvertedDoublePendulum-v2
+    metrics:
+    - type: mean_reward
+      value: 4884.17 +/- 4473.47
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **InvertedDoublePendulum-v2**
+This is a trained model of a **PPO** agent playing **InvertedDoublePendulum-v2**
+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 InvertedDoublePendulum-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env InvertedDoublePendulum-v2  -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 InvertedDoublePendulum-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env InvertedDoublePendulum-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env InvertedDoublePendulum-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env InvertedDoublePendulum-v2 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('clip_range', 0.4),
+             ('ent_coef', 1.05057e-06),
+             ('gae_lambda', 0.8),
+             ('gamma', 0.98),
+             ('learning_rate', 0.000155454),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 1),
+             ('n_epochs', 10),
+             ('n_steps', 128),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('vf_coef', 0.695929),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - InvertedDoublePendulum-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1535442608
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/InvertedDoublePendulum-v2__ppo__1535442608__1675794666
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - clip_range
+    - 0.4
+  - - ent_coef
+    - 1.05057e-06
+  - - gae_lambda
+    - 0.8
+  - - gamma
+    - 0.98
+  - - learning_rate
+    - 0.000155454
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 128
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - vf_coef
+    - 0.695929

env_kwargs.yml

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

ppo-InvertedDoublePendulum-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8972f61f41c920a87a3ff713eb4f8f83c83d8f907ae4f92b3cc6cef945f4d0
+size 155782

ppo-InvertedDoublePendulum-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

ppo-InvertedDoublePendulum-v2/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 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 0x7f8cd7f53ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8cd7f53f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8cd7f54040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8cd7f540d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f8cd7f54160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f8cd7f541f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8cd7f54280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8cd7f54310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f8cd7f543a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8cd7f54430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8cd7f544c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8cd7f54550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f8cd7f552c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            11
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000064,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1675794670108139045,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWV7wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXi9ob21lL3FnYWxsb3VlZGVjL2Vudl9iZW5jaG1hcmsvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjF4vaG9tZS9xZ2FsbG91ZWRlYy9lbnZfYmVuY2htYXJrL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8kYCuxKygZhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "tensorboard_log": "runs/InvertedDoublePendulum-v2__ppo__1535442608__1675794666/InvertedDoublePendulum-v2",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAH5/rxKGkLE/nhiDG/2qd789TlyYYlGWP6nXMf3c/+8/0+YI2g3+7z/jBvgd7e/FP5Yh3TnEDSe/PplcjV02sr8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -6.4000000000064e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 78130,
+    "n_steps": 128,
+    "gamma": 0.98,
+    "gae_lambda": 0.8,
+    "ent_coef": 1.05057e-06,
+    "vf_coef": 0.695929,
+    "max_grad_norm": 0.5,
+    "batch_size": 512,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-InvertedDoublePendulum-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f434602419c2ed4e8cacd27e2d33b2ee89a90f6b85d27f7884807224263e60b8
+size 90352

ppo-InvertedDoublePendulum-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbb5731a13b7af97eaa795d6caf10aef97e2db419aad23ceb6d50b13f8cddd6
+size 44414

ppo-InvertedDoublePendulum-v2/pytorch_variables.pth

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

ppo-InvertedDoublePendulum-v2/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b0f742505e17143c49f3f8658e5091c410b74e234d48ea85fc6a7818882e18
+size 133920

results.json

@@ -0,0 +1 @@
+{"mean_reward": 4884.1650905, "std_reward": 4473.470606221856, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T15:27:06.036111"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6c8144aea048276b2b9bb3815c24d9653e913415250d3ade33ca78295ac132
+size 288125

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f075dac67f016292f57f39d5aeb9948bcedab7c7fb1fded6c628896f39f1cf
+size 4425