Push PPO Agent for FrozenLakev1

PPO_for_FrozenLake.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772318a488fabfe1ed63f38fcfbc65d315422c758351f5438fa1582edb1325d3
+size 156898

PPO_for_FrozenLake/_stable_baselines3_version

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

PPO_for_FrozenLake/data

@@ -0,0 +1,90 @@
+{
+    "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 0x7f295855bd30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f295855bdc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f295855be50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f295855bee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f295855bf70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2958561040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f29585610d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2958561160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f29585611f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2958561280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2958561310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29585613a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f295855f0c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 16,
+        "_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": 10,
+    "num_timesteps": 1003520,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1675719583628130383,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVwwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAAAAAAAAAAAAACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADQAAAAAAAAAOAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksKhZSMAUOUdJRSlC4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYKAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwqFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP/AAAAAAAACMAWyUSxSMAXSUR0B9/vCHh0hedX2UKGgGRz/wAAAAAAAAaAdLFmgIR0B9/uGATZg5dX2UKGgGRwAAAAAAAAAAaAdLMGgIR0B9/vywwCbMdX2UKGgGRz/wAAAAAAAAaAdLDmgIR0B9/vUONHYpdX2UKGgGRz/wAAAAAAAAaAdLNWgIR0B9/zCN0eU7dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B9/x9YwIt2dX2UKGgGRz/wAAAAAAAAaAdLNmgIR0B9/062fChwdX2UKGgGRz/wAAAAAAAAaAdLEWgIR0B9/0SSNfgKdX2UKGgGRz/wAAAAAAAAaAdLDmgIR0B9/3XVbzK+dX2UKGgGRz/wAAAAAAAAaAdLFmgIR0B9/2ij+JgtdX2UKGgGRz/wAAAAAAAAaAdLK2gIR0B9/5cbBGhFdX2UKGgGRz/wAAAAAAAAaAdLHGgIR0B9/33N9ph4dX2UKGgGRz/wAAAAAAAAaAdLJmgIR0B9/58eCCjDdX2UKGgGRwAAAAAAAAAAaAdLO2gIR0B9/6THKfWddX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B9///KhcqwdX2UKGgGRz/wAAAAAAAAaAdLE2gIR0B+AANQTEiudX2UKGgGRwAAAAAAAAAAaAdLJmgIR0B+ADY9Pk7wdX2UKGgGRwAAAAAAAAAAaAdLL2gIR0B+ADBzmwJPdX2UKGgGRz/wAAAAAAAAaAdLImgIR0B+AEihWYF8dX2UKGgGRz/wAAAAAAAAaAdLNGgIR0B+AHRJEpiJdX2UKGgGRwAAAAAAAAAAaAdLS2gIR0B+AJzCDVYqdX2UKGgGRwAAAAAAAAAAaAdLE2gIR0B+ANE+gUUPdX2UKGgGRwAAAAAAAAAAaAdLJ2gIR0B+APhZQpF1dX2UKGgGRz/wAAAAAAAAaAdLK2gIR0B+AOBkI5YHdX2UKGgGRz/wAAAAAAAAaAdLH2gIR0B+AOnAIppfdX2UKGgGRz/wAAAAAAAAaAdLFmgIR0B+AQrvsqrjdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+AUd5prULdX2UKGgGRz/wAAAAAAAAaAdLDGgIR0B+ARt8/lhgdX2UKGgGRz/wAAAAAAAAaAdLYWgIR0B+AYQOFxn4dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+AXnied08dX2UKGgGRz/wAAAAAAAAaAdLFWgIR0B+AbIEKVpsdX2UKGgGRz/wAAAAAAAAaAdLTGgIR0B+AbfBN21VdX2UKGgGRz/wAAAAAAAAaAdLKWgIR0B+AdgKF7D3dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+AfogV45cdX2UKGgGRz/wAAAAAAAAaAdLK2gIR0B+AfN+so2GdX2UKGgGRz/wAAAAAAAAaAdLQmgIR0B+Ahz3h4t6dX2UKGgGRz/wAAAAAAAAaAdLJmgIR0B+AjdoFmnPdX2UKGgGRz/wAAAAAAAAaAdLD2gIR0B+AkUSIxgzdX2UKGgGRwAAAAAAAAAAaAdLLGgIR0B+AospXp4bdX2UKGgGRz/wAAAAAAAAaAdLK2gIR0B+Aovi97F9dX2UKGgGRwAAAAAAAAAAaAdLEmgIR0B+Ao8U21lYdX2UKGgGRwAAAAAAAAAAaAdLE2gIR0B+AqF/QSi/dX2UKGgGRwAAAAAAAAAAaAdLWmgIR0B+ArZVXFLndX2UKGgGRz/wAAAAAAAAaAdLDWgIR0B+AsrQPZqVdX2UKGgGRz/wAAAAAAAAaAdLIGgIR0B+ArjaPCEYdX2UKGgGRz/wAAAAAAAAaAdLXWgIR0B+ArulXRw7dX2UKGgGRz/wAAAAAAAAaAdLFWgIR0B+AvnW8RL9dX2UKGgGRz/wAAAAAAAAaAdLN2gIR0B+Au4qgAZLdX2UKGgGRz/wAAAAAAAAaAdLLmgIR0B+AtyXD3uedX2UKGgGRz/wAAAAAAAAaAdLGGgIR0B+Ax+TeO4odX2UKGgGRwAAAAAAAAAAaAdLF2gIR0B+A2qjrRjSdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+A3kRzzVddX2UKGgGRwAAAAAAAAAAaAdLImgIR0B+A4L9deIEdX2UKGgGRz/wAAAAAAAAaAdLOGgIR0B+A6lyimEXdX2UKGgGRz/wAAAAAAAAaAdLNGgIR0B+A7+MqBmPdX2UKGgGRz/wAAAAAAAAaAdLHGgIR0B+A/K/20zCdX2UKGgGRz/wAAAAAAAAaAdLGGgIR0B+A+4Wk8A8dX2UKGgGRz/wAAAAAAAAaAdLK2gIR0B+A/B2wFC+dX2UKGgGRz/wAAAAAAAAaAdLRmgIR0B+BBOUMXrMdX2UKGgGRz/wAAAAAAAAaAdLQWgIR0B+A/r1M/QjdX2UKGgGRz/wAAAAAAAAaAdLEWgIR0B+BBFkQPI5dX2UKGgGRz/wAAAAAAAAaAdLP2gIR0B+BCDFqBVddX2UKGgGRz/wAAAAAAAAaAdLDmgIR0B+BDHFPznSdX2UKGgGRz/wAAAAAAAAaAdLGWgIR0B+BCH31zySdX2UKGgGRz/wAAAAAAAAaAdLIWgIR0B+BCI7/4qPdX2UKGgGRwAAAAAAAAAAaAdLTmgIR0B+BE7r9l3AdX2UKGgGRz/wAAAAAAAAaAdLCmgIR0B+BEGnn+yadX2UKGgGRz/wAAAAAAAAaAdLE2gIR0B+BE0uUUwjdX2UKGgGRz/wAAAAAAAAaAdLKGgIR0B+BLmITGo8dX2UKGgGRz/wAAAAAAAAaAdLI2gIR0B+BKqOtGNJdX2UKGgGRz/wAAAAAAAAaAdLCmgIR0B+BPA1vVEvdX2UKGgGRwAAAAAAAAAAaAdLHmgIR0B+BOv5gw49dX2UKGgGRz/wAAAAAAAAaAdLJmgIR0B+BOS9ugpSdX2UKGgGRwAAAAAAAAAAaAdLJmgIR0B+BQi/wiJPdX2UKGgGRz/wAAAAAAAAaAdLJWgIR0B+BQ+A3DNydX2UKGgGRz/wAAAAAAAAaAdLEmgIR0B+BUkhRqGldX2UKGgGRz/wAAAAAAAAaAdLEmgIR0B+BUHY6GQCdX2UKGgGRz/wAAAAAAAAaAdLEGgIR0B+BVlxwQ18dX2UKGgGRz/wAAAAAAAAaAdLPmgIR0B+BXAXVLBbdX2UKGgGRz/wAAAAAAAAaAdLH2gIR0B+BY0qH447dX2UKGgGRz/wAAAAAAAAaAdLGmgIR0B+BcfuCwr2dX2UKGgGRz/wAAAAAAAAaAdLJGgIR0B+BgXEZR8/dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+Bhvn8sMBdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+BjAM2FWXdX2UKGgGRz/wAAAAAAAAaAdLF2gIR0B+BkoKD017dX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+BjO+qR2bdX2UKGgGRwAAAAAAAAAAaAdLLmgIR0B+Bowvg3tKdX2UKGgGRwAAAAAAAAAAaAdLNWgIR0B+BnwkPczqdX2UKGgGRz/wAAAAAAAAaAdLRWgIR0B+BoRL9MsZdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0B+BsXZXdTHdX2UKGgGRz/wAAAAAAAAaAdLH2gIR0B+BvROUMXrdX2UKGgGRz/wAAAAAAAAaAdLF2gIR0B+Bvn3cpLFdX2UKGgGRwAAAAAAAAAAaAdLTmgIR0B+BxwfhddFdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0B+Bwh0Qsf8dX2UKGgGRz/wAAAAAAAAaAdLNmgIR0B+BzH5rP+odX2UKGgGRz/wAAAAAAAAaAdLG2gIR0B+Bxd5Y5ktdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B+B10YCQtBdX2UKGgGRz/wAAAAAAAAaAdLDGgIR0B+B11LamGedX2UKGgGRz/wAAAAAAAAaAdLFGgIR0B+B4Jb+tKadX2UKGgGRz/wAAAAAAAAaAdLHGgIR0B+B55t3wCsdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 392,
+    "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_for_FrozenLake/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3798c69dd57a888e8498a16210d8dcbe5821e2ce34ae0d05c9d75cfb01653f3
+size 96121

PPO_for_FrozenLake/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8352971076ede3979690ed616fab9a88e16de438844cb7b742b43f516a2fabca
+size 47489

PPO_for_FrozenLake/pytorch_variables.pth

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

PPO_for_FrozenLake/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

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: 0.70 +/- 0.46
+      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 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 0x7f295855bd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f295855bdc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f295855be50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f295855bee0>", "_build": "<function ActorCriticPolicy._build at 0x7f295855bf70>", "forward": "<function ActorCriticPolicy.forward at 0x7f2958561040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f29585610d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2958561160>", "_predict": "<function ActorCriticPolicy._predict at 0x7f29585611f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2958561280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2958561310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29585613a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f295855f0c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 16, "_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": 10, "num_timesteps": 1003520, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675719583628130383, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVwwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAAAAAAAAAAAAACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADQAAAAAAAAAOAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksKhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYKAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwqFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 392, "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"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.7, "std_reward": 0.45825756949558405, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-06T21:53:11.288890"}