Upload PPO Mountain Car agent trained for 10M steps with default hyperparameters

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: -97.60 +/- 7.05
+      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 0x154206820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1542068b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x154206940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1542069d0>", "_build": "<function ActorCriticPolicy._build at 0x154206a60>", "forward": "<function ActorCriticPolicy.forward at 0x154206af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x154206b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x154206c10>", "_predict": "<function ActorCriticPolicy._predict at 0x154206ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x154206d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x154206dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x154206e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x15420b400>"}, "verbose": 0, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "dtype": "float32", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 10000384, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677536469495927000, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAADTEBz5eoBo9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="}, "_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": -3.8399999999993994e-05, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 48830, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:39:35 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T8103", "Python": "3.9.7", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.23.5", "Gym": "0.21.0"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929198cfb613bf9cfc20ff9ccf09873177f0d8305d42644cdfcbb83e78528f09
+size 134665

ppo-MountainCar-v0/_stable_baselines3_version

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

ppo-MountainCar-v0/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 0x154206820>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1542068b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x154206940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1542069d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x154206a60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x154206af0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x154206b80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x154206c10>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x154206ca0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x154206d30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x154206dc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x154206e50>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x15420b400>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "num_timesteps": 10000384,
+    "_total_timesteps": 10000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1677536469495927000,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAADTEBz5eoBo9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
+    },
+    "_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": -3.8399999999993994e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFnAAAAAAACMAWyUS2eMAXSUR0CtB+9pRGc4dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtB/YzabnYdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtB/u14Pf9dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCAKGDcubdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCBQm/nGLdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtCBtP557gdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCCJGvwEydX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCCkZiuuBdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0CtCC8M3IdVdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CtCDSmhufmdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0CtCDrFOwgUdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCEGJemeldX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCEhQm/nGdX2UKGgGR8BZQAAAAAAAaAdLZWgIR0CtCE70Fr2ydX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCFYtQKrrdX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CtCGXXAdn1dX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtCGu3+dbxdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCQUALiMpdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtCQqYAsCldX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtCRAeii7DdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0CtCRZOzposdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCR1NHpbEdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCSSKm8/VdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CtCSrJjlPrdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CtCTDwx33YdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0CtCUDxb0OFdX2UKGgGR8BWwAAAAAAAaAdLW2gIR0CtCUcLa24NdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtCUyLyc0+dX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtCVJJXhfjdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CtCVfoq0+ldX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtCV2lEZzgdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtCWSpR4yHdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtCWuJ1q33dX2UKGgGR8BaQAAAAAAAaAdLaWgIR0CtCXJtix3WdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtCXlBppN9dX2UKGgGR8BXgAAAAAAAaAdLXmgIR0CtCX9pRGc4dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtCZCrT6SDdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCZee4Cp4dX2UKGgGR8BWAAAAAAAAaAdLWGgIR0CtCjCY9gWrdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCjeo99tudX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtCj6LOzIFdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCkV3MY/FdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCkxYRujzdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtClNDUmUodX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtClpjUd7wdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CtCmFzdUKidX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtCnQbEP1+dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCns67ulXdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCoJxNqQBdX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CtCowco6S1dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCpP24/eMdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCpsJhOQAdX2UKGgGR8BXQAAAAAAAaAdLXWgIR0CtCqFd9lVcdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCqhPTG5udX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtCq9JJ5E/dX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtCrbFCLMtdX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CtCsdIwudxdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtCszpPhybdX2UKGgGR8BVAAAAAAAAaAdLVGgIR0CtCtKPn0TUdX2UKGgGR8BXwAAAAAAAaAdLX2gIR0CtC5jtXxOMdX2UKGgGR8BYwAAAAAAAaAdLY2gIR0CtC5+UpuuSdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtC6ZcC5mRdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtC60voNd7dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtC7QlSjxkdX2UKGgGR8BbgAAAAAAAaAdLbmgIR0CtC7vmHP/rdX2UKGgGR8BYQAAAAAAAaAdLYWgIR0CtC8J9AooedX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CtC9IcinpCdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtC9kL6UJOdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtC+APVd5ZdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtC+XiBGx2dX2UKGgGR8BVgAAAAAAAaAdLVmgIR0CtC+ukLx7RdX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtC/GkN4JNdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtC/iuEEkjdX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtC/+fI0ZWdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDAaWPcSHdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDA2SlnAZdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDBTLW7OFdX2UKGgGR8BlIAAAAAAAaAdLqWgIR0CtDCr4vexfdX2UKGgGR8BUwAAAAAAAaAdLU2gIR0CtDDCcXm/4dX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtDMxgy/KydX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDNNYbKigdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDNo8QqZudX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDOEWhysCdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDOfp2U0OdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CtDO4MWoFWdX2UKGgGR8BWgAAAAAAAaAdLWmgIR0CtDPP+n62wdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtDQTLW7OFdX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CtDQrxZuAJdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDRHG8274dX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtDRiAlOXWdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtDR9jwx33dX2UKGgGR8BVwAAAAAAAaAdLV2gIR0CtDSVP3ztkdX2UKGgGR8BZgAAAAAAAaAdLZmgIR0CtDSwZn+Q2dX2UKGgGR8BaAAAAAAAAaAdLaGgIR0CtDTMH0K7adX2UKGgGR8BXAAAAAAAAaAdLXGgIR0CtDTkh7mdRdX2UKGgGR8BWwAAAAAAAaAdLW2gIR0CtDT8nuy/sdX2UKGgGR8BVQAAAAAAAaAdLVWgIR0CtDUTNUwSKdX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDVWBz3h5dX2UKGgGR8BZwAAAAAAAaAdLZ2gIR0CtDVxlpXZHdX2UKGgGR8BWAAAAAAAAaAdLWGgIR0CtDWJBPbfxdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 48830,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6beeb46d07b25f7f928d658ce4c5250eca3204a00a89f30fb06b5ac9e8add5
+size 80889

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eeaf3fe5b5e00641ec06e4429f2e3cafa5e9341248324896332d7aa0b47408e
+size 39937

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 +1,7 @@
+- OS: macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:39:35 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T8103
+- Python: 3.9.7
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1
+- GPU Enabled: False
+- Numpy: 1.23.5
+- Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": -97.6, "std_reward": 7.045565981523415, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T00:34:48.087097"}