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 0x7d14d8357240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d14d83572e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d14d8357380>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d14d8357420>", "_build": "<function ActorCriticPolicy._build at 0x7d14d83574c0>", "forward": "<function ActorCriticPolicy.forward at 0x7d14d8357560>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d14d8357600>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d14d83576a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d14d8357740>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d14d83577e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d14d8357880>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d14d8357920>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d14d8412b40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1767332612746255038, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.983616, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVCAQAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHLQAAAAAACMAWyUTS0BjAF0lEdApHPZK8L8aXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR0aVpKzzF1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdGkrf+CLdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHRo7kn1F3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR0aI+nqFB1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdGhnBciXdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHRoQg9vCXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR0aBVdX1d1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdGfoicG1dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHRnvOQhfXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR0Z1Oj7AN1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdGcjzI3jdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHRm+ZgG8nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR0ZtQ9A5d1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdGatT1kEdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHRmivgWJ3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR1dNA1Nxl1fZQoaAZHQH9AAAAAAABoB030AWgIR0CkdjBFNL13dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHYwGOdXk3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR2L92ovSN1fZQoaAZHQH9AAAAAAABoB030AWgIR0Ckdi+MZP2xdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHYvaHsTnXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR2L0Yj0MB1fZQoaAZHQH9AAAAAAABoB030AWgIR0Ckdi8bzbvgdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHYu8TSLInV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR2LsfJV811fZQoaAZHQH9AAAAAAABoB030AWgIR0Ckdi5gogFHdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHYuMyad+XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR2Lgssg+11fZQoaAZHQH9AAAAAAABoB030AWgIR0Ckdi3nyNGWdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdApHYtwvQF93V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQKR2LaNdZ7p1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 249, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_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]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAIAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9ac7a8262a5dbf6a1e51fd8a13d6691ba8d8286058a8d629c267a82ab09de6
+size 138044

ppo-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-CartPole-v1/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7d14d8357240>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d14d83572e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d14d8357380>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d14d8357420>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d14d83574c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d14d8357560>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d14d8357600>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d14d83576a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d14d8357740>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d14d83577e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d14d8357880>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d14d8357920>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d14d8412b40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 16384,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1767332612746255038,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.983616,
+    "_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": 249,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_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]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAIAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEyL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTIvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e6cd30661c2ed97ddb7205df0521afe343112fc4b5d698471ce2ed9c927c3e
+size 83575

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee4bceaaac992ed354799d8851a1dc466fe2e4b336ea56995f2d4fe9b505042
+size 41535

ppo-CartPole-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
+size 1261

ppo-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025
+- Python: 3.12.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.9.0+cu126
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.2
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-02T05:52:00.521588"}