first commit

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **CartPole-v1**
+This is a trained model of a **PPO** agent playing **CartPole-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 0x7f57e28ef670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57e28ef700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57e28ef790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57e28ef820>", "_build": "<function ActorCriticPolicy._build at 0x7f57e28ef8b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f57e28ef940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f57e28ef9d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57e28efa60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f57e28efaf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57e28efb80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57e28efc10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57e28efca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f57e28e9930>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673877406734027748, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 256, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo_CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f66da50a5e95f6d5fd8701ce209dfb7b3be51008ea088725010a9bc3998bc8
+size 137900

ppo_CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

ppo_CartPole-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 0x7f57e28ef670>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57e28ef700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57e28ef790>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57e28ef820>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f57e28ef8b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f57e28ef940>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f57e28ef9d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57e28efa60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f57e28efaf0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57e28efb80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57e28efc10>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57e28efca0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f57e28e9930>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1673877406734027748,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 256,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "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
+}

ppo_CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c441e9bce72da04b2040a8cdad202ee9738ab37c201a82c73bdc49aa1bd602e7
+size 82809

ppo_CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19588f782566a4923ca086bc427adaf8a49ec5c1fafefa52709f97703fd6edfe
+size 40833

ppo_CartPole-v1/pytorch_variables.pth

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

ppo_CartPole-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cu116
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-16T14:03:35.790141"}