new!

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- FrozenLake-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1
+      type: FrozenLake-v1
+    metrics:
+    - type: mean_reward
+      value: 0.10 +/- 0.30
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **FrozenLake-v1**
+This is a trained model of a **PPO** agent playing **FrozenLake-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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f44edb329d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f44edb32a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f44edb32af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f44edb32b80>", "_build": "<function ActorCriticPolicy._build at 0x7f44edb32c10>", "forward": "<function ActorCriticPolicy.forward at 0x7f44edb32ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f44edb32d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f44edb32dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f44edb32e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f44edb32ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f44edb32f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f44edb2f420>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLQIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 64, "_shape": [], "dtype": "int64", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670280384289131256, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAADgAAAAAAAAAIQAAAAAAAAA8AAAAAAAAABEAAAAAAAAAAAAAAAAAAAA6AAAAAAAAABsAAAAAAAAAKwAAAAAAAAAIAAAAAAAAAD0AAAAAAAAAOwAAAAAAAAApAAAAAAAAACAAAAAAAAAAOgAAAAAAAAA+AAAAAAAAABEAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 128, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-FrozenLake-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fc4559af8a85b33b0724ff7056ab2e27192da9997a153d1b509b08a48a2eca
+size 229978

ppo-FrozenLake-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-FrozenLake-v1/data

@@ -0,0 +1,89 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f44edb329d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f44edb32a60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f44edb32af0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f44edb32b80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f44edb32c10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f44edb32ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f44edb32d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f44edb32dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f44edb32e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f44edb32ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f44edb32f70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f44edb2f420>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLQIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 64,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 507904,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1670280384289131256,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAADgAAAAAAAAAIQAAAAAAAAA8AAAAAAAAABEAAAAAAAAAAAAAAAAAAAA6AAAAAAAAABsAAAAAAAAAKwAAAAAAAAAIAAAAAAAAAD0AAAAAAAAAOwAAAAAAAAApAAAAAAAAACAAAAAAAAAAOgAAAAAAAAA+AAAAAAAAABEAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_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:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHAAAAAAAAAACMAWyUS2SMAXSUR0Blv+CGvfTDdX2UKGgGRz/wAAAAAAAAaAdLJWgIR0BlwW3z+WGAdX2UKGgGRz/wAAAAAAAAaAdLFGgIR0Blv/OhTOxCdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0BlwUDKYAsDdX2UKGgGRz/wAAAAAAAAaAdLMGgIR0Blv9TUAks0dX2UKGgGRz/wAAAAAAAAaAdLXGgIR0BlwOGfwqiHdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlwarxRVIadX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlwecSXdCWdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlwRvHcUM5dX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0BlwqrWAf+1dX2UKGgGRz/wAAAAAAAAaAdLMmgIR0Blwh/iHZbqdX2UKGgGRwAAAAAAAAAAaAdLAWgIR0BlwigPEsJ6dX2UKGgGRz/wAAAAAAAAaAdLKGgIR0BlwUd5prULdX2UKGgGRz/wAAAAAAAAaAdLTWgIR0BlwThvR7Z4dX2UKGgGRz/wAAAAAAAAaAdLOmgIR0Blwd2gWac7dX2UKGgGRwAAAAAAAAAAaAdLAWgIR0BlweV1Oj7AdX2UKGgGRz/wAAAAAAAAaAdLKWgIR0Blwly7wrlOdX2UKGgGRz/wAAAAAAAAaAdLY2gIR0Blwj9CNS62dX2UKGgGRwAAAAAAAAAAaAdLJWgIR0Blwv2RJVbSdX2UKGgGRz/wAAAAAAAAaAdLP2gIR0BlwhSYPXkHdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlwupQ1rIpdX2UKGgGRwAAAAAAAAAAaAdLEmgIR0BlwcBIWgvldX2UKGgGRwAAAAAAAAAAaAdLBWgIR0BlwoVj7Q9idX2UKGgGRz/wAAAAAAAAaAdLUWgIR0BlwrR6Ww/xdX2UKGgGRz/wAAAAAAAAaAdLWmgIR0Blw7yhBZ6ldX2UKGgGRwAAAAAAAAAAaAdLC2gIR0BlwtfkWAPNdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0Blw9Sn+AEudX2UKGgGRwAAAAAAAAAAaAdLJmgIR0BlwmiaiKzidX2UKGgGRwAAAAAAAAAAaAdLVmgIR0BlxD7fpD/mdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlwlOCXhOydX2UKGgGRz/wAAAAAAAAaAdLO2gIR0Blw+mWMS9NdX2UKGgGRwAAAAAAAAAAaAdLFGgIR0Blwumm+CbudX2UKGgGRz/wAAAAAAAAaAdLKWgIR0Blw+oxYaHcdX2UKGgGRz/wAAAAAAAAaAdLPGgIR0Blw9qYZ2pydX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxQtxuKoAdX2UKGgGRz/wAAAAAAAAaAdLLmgIR0BlxZrtVrAQdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxCLCN0eVdX2UKGgGRz/wAAAAAAAAaAdLTWgIR0BlxA84gieNdX2UKGgGRz/wAAAAAAAAaAdLTmgIR0BlxUFINEw4dX2UKGgGRwAAAAAAAAAAaAdLR2gIR0BlxPeYUnG9dX2UKGgGRz/wAAAAAAAAaAdLKGgIR0BlxB6po9LYdX2UKGgGRwAAAAAAAAAAaAdLHGgIR0BlxLcKw6hhdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxOIbfgrIdX2UKGgGRz/wAAAAAAAAaAdLSGgIR0Blxf6l+EytdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxVYZEUj+dX2UKGgGRwAAAAAAAAAAaAdLCWgIR0BlxUp1A7gbdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxirNnoPkdX2UKGgGRz/wAAAAAAAAaAdLQGgIR0BlxgYUFjd6dX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0BlxvtF8XvZdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxupuMuOCdX2UKGgGRz/wAAAAAAAAaAdLL2gIR0Blxqv3ai9JdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlxZgE2YOUdX2UKGgGRz/wAAAAAAAAaAdLK2gIR0BlxYo9cKPXdX2UKGgGRwAAAAAAAAAAaAdLJWgIR0Blx0k4WDYidX2UKGgGRwAAAAAAAAAAaAdLL2gIR0BlxlCCz1K5dX2UKGgGRz/wAAAAAAAAaAdLK2gIR0BlxrhUBGQTdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0Blxx7LMcIadX2UKGgGRz/wAAAAAAAAaAdLImgIR0BlxqFCb+cZdX2UKGgGRwAAAAAAAAAAaAdLG2gIR0BlyBzBAOawdX2UKGgGRz/wAAAAAAAAaAdLT2gIR0Blx9KXfIjodX2UKGgGRz/wAAAAAAAAaAdLM2gIR0BlyDUgB91EdX2UKGgGRz/wAAAAAAAAaAdLUWgIR0Blx5frrxAjdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0Blx1O9FnZkdX2UKGgGRz/wAAAAAAAAaAdLGWgIR0Blx1/QSi/PdX2UKGgGRwAAAAAAAAAAaAdLJ2gIR0BlyEj3VTaTdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0Blx1BKL877dX2UKGgGRwAAAAAAAAAAaAdLGWgIR0BlyPW6K+BZdX2UKGgGRz/wAAAAAAAAaAdLU2gIR0BlyWnEVFhHdX2UKGgGRz/wAAAAAAAAaAdLPmgIR0BlyC0Y0l7ddX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlyFgDzRQadX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlyTFMqSX/dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlyQ5PuXu3dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlyggTyrggdX2UKGgGRz/wAAAAAAAAaAdLN2gIR0Blyc4T9KmLdX2UKGgGRz/wAAAAAAAAaAdLImgIR0BlyHGIbfgrdX2UKGgGRz/wAAAAAAAAaAdLPGgIR0BlyarFOwgUdX2UKGgGRwAAAAAAAAAAaAdLI2gIR0BlyWOU+s5odX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlyJflZHNHdX2UKGgGRz/wAAAAAAAAaAdLGWgIR0BlyP336AOKdX2UKGgGRwAAAAAAAAAAaAdLBWgIR0BlyMAT7EYPdX2UKGgGRz/wAAAAAAAAaAdLP2gIR0BlyYq/dqL1dX2UKGgGRz/wAAAAAAAAaAdLLWgIR0BlyLlzU7SzdX2UKGgGRz/wAAAAAAAAaAdLIWgIR0BlyWYYzi0fdX2UKGgGRz/wAAAAAAAAaAdLKmgIR0BlyrvoePq+dX2UKGgGRz/wAAAAAAAAaAdLX2gIR0BlyaNCJGe+dX2UKGgGRwAAAAAAAAAAaAdLKmgIR0Blyn/YJ3PidX2UKGgGRz/wAAAAAAAAaAdLK2gIR0Bly1Tzd1uBdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0BlypAyEcsEdX2UKGgGRwAAAAAAAAAAaAdLM2gIR0Bly1Z5iVjadX2UKGgGRz/wAAAAAAAAaAdLJmgIR0BlyiBiCrcTdX2UKGgGRz/wAAAAAAAAaAdLImgIR0Blyqfg75mAdX2UKGgGRz/wAAAAAAAAaAdLYmgIR0BlylR+BpYcdX2UKGgGRz/wAAAAAAAAaAdLGGgIR0BlzBAIIF/ydX2UKGgGRz/wAAAAAAAAaAdLS2gIR0Bly1u76Hj7dX2UKGgGRz/wAAAAAAAAaAdLJWgIR0Bly6GBWgezdX2UKGgGRz/wAAAAAAAAaAdLMmgIR0Blyu+yquKXdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0BlzBsEaESNdX2UKGgGRz/wAAAAAAAAaAdLOmgIR0BlzJiVjZtfdX2UKGgGRwAAAAAAAAAAaAdLRGgIR0BlyuIbfgrIdX2UKGgGRwAAAAAAAAAAaAdLB2gIR0BlzMz2vjffdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 128,
+    "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-FrozenLake-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918fed1bf7ca0b999573a71a087f76594d0954f25637e0dda178d4f752918e5a
+size 144889

ppo-FrozenLake-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fce996376b9db470404ac175b31a6b9d56f8ae37b87d5154076cb66ecb7880
+size 71745

ppo-FrozenLake-v1/pytorch_variables.pth

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

ppo-FrozenLake-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.15
+Stable-Baselines3: 1.6.2
+PyTorch: 1.12.1+cu113
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.1, "std_reward": 0.30000000000000004, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-05T22:49:43.554624"}