PPO MountainCar-v0 trained agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+    metrics:
+    - type: mean_reward
+      value: -200.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **MountainCar-v0**
+This is a trained model of a **PPO** agent playing **MountainCar-v0**
+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 0x7950467663b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795046766440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7950467664d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795046766560>", "_build": "<function ActorCriticPolicy._build at 0x7950467665f0>", "forward": "<function ActorCriticPolicy.forward at 0x795046766680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795046766710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7950467667a0>", "_predict": "<function ActorCriticPolicy._predict at 0x795046766830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7950467668c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795046766950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7950467669e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7950467704c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697029419908126511, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAMmqOr8RLja8ZBgVv13bXLuw/je/URxGu+LrwL4Ayj48xY8Av808SDs9Qhq/YiQkvPeiK7+SJj+8WUn7vuDcTDwE3x6/uVwuvNRtKr8zYqO5pq0Ov/avJ7wzowm/6fjnudGs/L6Uldq7d63kvp5rS7yHEua+8ZIfPIoVOb9K9mI8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_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": -0.04857599999999995, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwGkAAAAAAACMAWyUS8iMAXSUR0ByFFuivgWKdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByFFnrY5DJdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByFFffGdZrdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByFFXzUZvUdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG1bFCLMtdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG1P2wmmcdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG1F7Uoa2dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG08JUo8ZdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0xtYSxrdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0lw97ngdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0aisXBQdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0QK8cuKdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0H2RJVbdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByG0Aq/dqMdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGz5RCQcQdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGzyVfNRndX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGzqzJIUbdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGzkDIRywdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGzb0voNedX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByGzUSZjQRdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIlw4sEq2dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIllqagEmdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIlb0OEuhdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIlSIgvDhdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIlHww0wbdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIk76pHZsdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkwwj+rEdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkmb9ZRsdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkd3jdYXdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkWsRxtIdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkPRRdhRdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkIUrTYvdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIkAq/dqMdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIj544ZMtdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIjx5LRKIdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByIjqRlpXZdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKYzN2TxHdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKYoKD017dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKYeV9nbqdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKYUsWfsedX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKYKVpsXSdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKX+qBErodX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXzjFQ2udX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXpQk5ZKdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXhKlHjIdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXZ+QU5/dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXShJyyVdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXLhaTwEdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKXDqGDcudX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKW8zyjHodX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKW0iQkondX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByKWs1baAXdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByML49HMEBdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMLuIAOridX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMLkcS5AhdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMLayrxRVdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMLQa72+PdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMLEjxCpndX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMK5Yoy9FdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKvFFUhndX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKmgrYoRdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKfVZs9CdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKX5WRzSdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKQ8wHqvdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKJHiFTOdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMKCUX531dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMJ6E8JUpdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByMJyo4uK5dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOB40Mw10dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOBt2s7uEdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOBkFwDNhdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOBaOgg5jdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOBPsRg7YdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOBDqnm7rdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOA4VARkFdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAt29tdidX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAlIEr5JdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAdyT6i1dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAWN3np0dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAPGyX2NdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAHIIWxhdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByOAAR02cbdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByN/37DVH4dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByN/wH7gsLdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPw4Ia99MdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPwth/iHZdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPwju8brDdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPwaR6nivdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPwP8Q7LddX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPwEIPbwjdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPv5BTn7pdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvvCuU2UdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvmhdt2tdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvfYSQHSdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvYChew+dX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvRIBikPdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvJfYzzmdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPvCrLhaUdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPu6bvw3HdX2UKGgGR8BpAAAAAAAAaAdLyGgIR0ByPuyu6mO3dWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 67, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18feeb174c49f3fe4ba038fa54622ea129ee057ec653060b4559856f1e7e04b7
+size 135467

ppo-MountainCar-v0/_stable_baselines3_version

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

ppo-MountainCar-v0/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 0x7950467663b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795046766440>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7950467664d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795046766560>",
+        "_build": "<function ActorCriticPolicy._build at 0x7950467665f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x795046766680>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x795046766710>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7950467667a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x795046766830>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7950467668c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795046766950>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7950467669e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7950467704c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 524288,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1697029419908126511,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAMmqOr8RLja8ZBgVv13bXLuw/je/URxGu+LrwL4Ayj48xY8Av808SDs9Qhq/YiQkvPeiK7+SJj+8WUn7vuDcTDwE3x6/uVwuvNRtKr8zYqO5pq0Ov/avJ7wzowm/6fjnudGs/L6Uldq7d63kvp5rS7yHEua+8ZIfPIoVOb9K9mI8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_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": -0.04857599999999995,
+    "_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": 67,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "low_repr": "[-1.2  -0.07]",
+        "high_repr": "[0.6  0.07]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "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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"
+    }
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c4d669c384d6905c08fc438965a9ed1df9f4c34ea61ec7d9988ad6d2bebf17
+size 81273

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348277a182f39349131808e63e86bdd6fd00fc652585cb3178a452fbabb4f879
+size 40001

ppo-MountainCar-v0/pytorch_variables.pth

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

ppo-MountainCar-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-11T13:09:14.316710"}