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 +1,71 @@
+---
+library_name: stable-baselines3
+tags:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -77.70 +/- 6.68
+      name: mean_reward
+      verified: false
+---
+
+# **TRPO** Agent playing **Acrobot-v1**
+This is a trained model of a **TRPO** agent playing **Acrobot-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 trpo --env Acrobot-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Acrobot-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 trpo --env Acrobot-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Acrobot-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo trpo --env Acrobot-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo trpo --env Acrobot-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 100000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - device
+    - auto
+  - - env
+    - Acrobot-v1
+  - - 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
+    - 1496881724
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Acrobot-v1__trpo__1496881724__1670945156
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,11 @@
+!!python/object/apply:collections.OrderedDict
+- - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 100000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc133b1eeacf9b4c8c0899aaae942c041ad382f3feda265b0a4564d6dd6fe5f
+size 939139

results.json

@@ -0,0 +1 @@
+{"mean_reward": -77.7, "std_reward": 6.679071791798618, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T17:13:41.640645"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d885b7ab91819b0918f48e7f1721b2561429b20665cd622885e2101315fdca4
+size 19809

trpo-Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617d3a594e6ed3048240798a32f48433a813c21ff7186cca408cf15ee479745b
+size 101224

trpo-Acrobot-v1/_stable_baselines3_version

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

trpo-Acrobot-v1/data

@@ -0,0 +1,95 @@
+{
+    "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 0x7fb0d2e8fd30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb0d2e8fdc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb0d2e8fe50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb0d2e8fee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb0d2e8ff70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb0d2e91040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb0d2e910d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb0d2e91160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb0d2e911f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb0d2e91280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb0d2e91310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb0d2e913a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb0d2e90f40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 100352,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670945159256849687,
+    "learning_rate": 0.001,
+    "tensorboard_log": "runs/Acrobot-v1__trpo__1496881724__1670945156/Acrobot-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAAnhfz/xzPs8Xyt/P/fWpD0vuoO9z4qXu9D/fz+/VB27B75/P4m9Nz3mdNg8ckTHPJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAksGhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 49,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.0,
+    "max_grad_norm": 0.0,
+    "normalize_advantage": true,
+    "batch_size": 128,
+    "cg_max_steps": 15,
+    "cg_damping": 0.1,
+    "line_search_shrinking_factor": 0.8,
+    "line_search_max_iter": 10,
+    "target_kl": 0.01,
+    "n_critic_updates": 10,
+    "sub_sampling_factor": 1
+}

trpo-Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a558874c787ab91bc5ebc4285382b94f708dfac54d26742bbc38c77abc57ca
+size 42415

trpo-Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c465ad83368758c33c7ed5c495b0fbcd5b051b62b30dd374dbc2c0a87a5458
+size 42049

trpo-Acrobot-v1/pytorch_variables.pth

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

trpo-Acrobot-v1/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

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e364fb4d9ce449c7d102a538c957f24fb967f7026d55899c445f4bee411d55ab
+size 4105