Upload PPO CartPole-v1 trained agent

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 0x7f2165e76430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2165e764c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2165e76550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2165e765e0>", "_build": "<function ActorCriticPolicy._build at 0x7f2165e76670>", "forward": "<function ActorCriticPolicy.forward at 0x7f2165e76700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2165e76790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2165e76820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2165e768b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2165e76940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2165e769d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2165e76a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2165e734b0>"}, "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": 1, "num_timesteps": 10240, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675953924114954790, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAC6arT4gizU9n53svZn17TyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 40, "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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+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 sha256:9f2b8b5cd1dacfae50e178a9cdbb2a4802a026037ec83e9e88a9f6443b082afd
+size 137417

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 0x7f2165e76430>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2165e764c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2165e76550>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2165e765e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f2165e76670>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2165e76700>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2165e76790>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2165e76820>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f2165e768b0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2165e76940>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2165e769d0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2165e76a60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2165e734b0>"
+    },
+    "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": 1,
+    "num_timesteps": 10240,
+    "_total_timesteps": 10000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1675953924114954790,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAC6arT4gizU9n53svZn17TyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 40,
+    "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 sha256:99541df447975b546b7f2b4720cea0e4b84bbed3d87c685d37694b593fa98057
+size 82809

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bcec88cafef6cd7d69cff79cc05409b574d977959a704a88ce989f2cfd0622
+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-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.10
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+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": "2023-02-09T14:46:04.539425"}