push Acrobot-v1 model

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -73.20 +/- 7.79
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **Acrobot-v1**
+This is a trained model of a **PPO** agent playing **Acrobot-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"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 0x291665fc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x291666050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2916660e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x291666170>", "_build": "<function ActorCriticPolicy._build at 0x291666200>", "forward": "<function ActorCriticPolicy.forward at 0x291666290>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x291666320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2916663b0>", "_predict": "<function ActorCriticPolicy._predict at 0x291666440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2916664d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x291666560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x2916665f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x29165b040>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721723414775052000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x2912aa680>", "reset": "<function RolloutBuffer.reset at 0x2912aa710>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x2912aa7a0>", "add": "<function RolloutBuffer.add at 0x2912aa830>", "get": "<function RolloutBuffer.get at 0x2912aa8c0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x2912aa950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2912a3d00>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "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:": "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"}, "system_info": {"OS": "macOS-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103", "Python": "3.10.8", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

ppo_Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95122ff432cf333e3ca0d3fd2194632f432cb22766903167b6ce424e32b1c2d1
+size 146103

ppo_Acrobot-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

ppo_Acrobot-v1/data

@@ -0,0 +1,112 @@
+{
+    "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 0x291665fc0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x291666050>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2916660e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x291666170>",
+        "_build": "<function ActorCriticPolicy._build at 0x291666200>",
+        "forward": "<function ActorCriticPolicy.forward at 0x291666290>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x291666320>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2916663b0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x291666440>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2916664d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x291666560>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x2916665f0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x29165b040>"
+    },
+    "verbose": 2,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1721723414775052000,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_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": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "rollout_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
+        "__init__": "<function RolloutBuffer.__init__ at 0x2912aa680>",
+        "reset": "<function RolloutBuffer.reset at 0x2912aa710>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x2912aa7a0>",
+        "add": "<function RolloutBuffer.add at 0x2912aa830>",
+        "get": "<function RolloutBuffer.get at 0x2912aa8c0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x2912aa950>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x2912a3d00>"
+    },
+    "rollout_buffer_kwargs": {},
+    "batch_size": 64,
+    "n_epochs": 4,
+    "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:": "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"
+    }
+}

ppo_Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4f18d0df19366716a2cad62986246e3ecafee30d7315827a2f87b333d16606
+size 85418

ppo_Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e01d34e8f8349240089591f9f3c9c8630e84d917bee83e6fa5db41a5f4df8be
+size 42354

ppo_Acrobot-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
+size 864

ppo_Acrobot-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: macOS-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103
+- Python: 3.10.8
+- Stable-Baselines3: 2.3.2
+- PyTorch: 2.3.1
+- GPU Enabled: False
+- Numpy: 1.26.2
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -73.2, "std_reward": 7.794870107962031, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-23T16:56:26.357304"}