first try RL agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 263.14 +/- 16.19
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+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 0x7f637b277940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f637b2779d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f637b277a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f637b277af0>", "_build": "<function ActorCriticPolicy._build at 0x7f637b277b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f637b277c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f637b277ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f637b277d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f637b277dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f637b277e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f637b277ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f637b277f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f637b26cf30>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676027265271243051, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": 252, "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-5.10.147+-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"}}

first try.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ad5492bec0448aec35d0292ff4ff23d3d75f657fe067e30b486fb8f3b964e4
+size 147400

first try/_stable_baselines3_version

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

first try/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 0x7f637b277940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f637b2779d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f637b277a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f637b277af0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f637b277b80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f637b277c10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f637b277ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f637b277d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f637b277dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f637b277e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f637b277ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f637b277f70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f637b26cf30>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_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": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1676027265271243051,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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:": "gAWVbRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIa5p3nKKzUkCUhpRSlIwBbJRLyYwBdJRHQJwZdG7SRbN1fZQoaAZoCWgPQwjp1QCloY1vQJSGlFKUaBVNTwFoFkdAnBndKZlWfnV9lChoBmgJaA9DCHtoHyv4nURAlIaUUpRoFUu/aBZHQJwZ5/J/5L11fZQoaAZoCWgPQwg9mBQfnzBRQJSGlFKUaBVLsmgWR0CcGnIwM6RydX2UKGgGaAloD0MIFNGvrZ9kb0CUhpRSlGgVTUwBaBZHQJwafp2U0N11fZQoaAZoCWgPQwhmhLcHIRxxQJSGlFKUaBVNEgFoFkdAnB1fsqril3V9lChoBmgJaA9DCFxzR/9LinJAlIaUUpRoFU0dAWgWR0CcHXf8dgfEdX2UKGgGaAloD0MIWI/7VusIbkCUhpRSlGgVTXEBaBZHQJwexhd+ocd1fZQoaAZoCWgPQwhU/UrnA5pyQJSGlFKUaBVL9GgWR0CcINyyD7IldX2UKGgGaAloD0MIEojX9YvbbECUhpRSlGgVTRIBaBZHQJwhEm6XjVB1fZQoaAZoCWgPQwjXT/9ZM8FyQJSGlFKUaBVNbwFoFkdAnCETBl+VknV9lChoBmgJaA9DCHmu78NBS1NAlIaUUpRoFUvMaBZHQJwiNHQQcxV1fZQoaAZoCWgPQwjf/IaJBhVxQJSGlFKUaBVNFQFoFkdAnCJN/J/5L3V9lChoBmgJaA9DCJEMObYez3JAlIaUUpRoFU0dAWgWR0CcImmNBF/hdX2UKGgGaAloD0MIYwtBDkq3bUCUhpRSlGgVTS4BaBZHQJwjt2ZAprl1fZQoaAZoCWgPQwgYIqevp31xQJSGlFKUaBVNFwFoFkdAnCRT+NtIkXV9lChoBmgJaA9DCF980R4vnnFAlIaUUpRoFU0UAWgWR0CcJJAD7qIKdX2UKGgGaAloD0MIVBuciP7CbECUhpRSlGgVTR4BaBZHQJwk3SPU8V51fZQoaAZoCWgPQwjrcd9qnfA7QJSGlFKUaBVNIQFoFkdAnCVSj59E1HV9lChoBmgJaA9DCJXYtb0dJ3FAlIaUUpRoFU2CAWgWR0CcJWkWhysCdX2UKGgGaAloD0MI6KT3jS+5b0CUhpRSlGgVTScBaBZHQJwldkkKNQ11fZQoaAZoCWgPQwiX4T/dgCdyQJSGlFKUaBVNCQFoFkdAnCZ59d/rjnV9lChoBmgJaA9DCD3X9+Gg/W5AlIaUUpRoFU0iAWgWR0CcJxIomXw9dX2UKGgGaAloD0MIzT6PUV7OcECUhpRSlGgVTSUBaBZHQJwoFXcQAdZ1fZQoaAZoCWgPQwiismFNZcBwQJSGlFKUaBVNNwFoFkdAnCpocFQl8nV9lChoBmgJaA9DCK/qrBZYvHBAlIaUUpRoFU0XAWgWR0CcKmXlbNbDdX2UKGgGaAloD0MISE4mbhUWSkCUhpRSlGgVS9xoFkdAnCrMhX8wYnV9lChoBmgJaA9DCE0s8BXdam1AlIaUUpRoFU1GAWgWR0CcKvFsYVIqdX2UKGgGaAloD0MIDLH6IwzrbkCUhpRSlGgVTVwBaBZHQJwrjGGVRk51fZQoaAZoCWgPQwiD+MCO/8NwQJSGlFKUaBVNBwFoFkdAnCuWmLtNSXV9lChoBmgJaA9DCPBrJAnC+VRAlIaUUpRoFUvYaBZHQJwr67Bfrrx1fZQoaAZoCWgPQwg491ePe6huQJSGlFKUaBVNSAFoFkdAnCwvjsD4g3V9lChoBmgJaA9DCGEcXDpmcG9AlIaUUpRoFU0pAWgWR0CcLY1LamGedX2UKGgGaAloD0MI5zki3yUub0CUhpRSlGgVTRcBaBZHQJwt0uVX3g11fZQoaAZoCWgPQwg1zxH5LmxyQJSGlFKUaBVNjAFoFkdAnC4ZcLSeAnV9lChoBmgJaA9DCD8cJES5N3BAlIaUUpRoFU1UAWgWR0CcLxRQJokBdX2UKGgGaAloD0MIJxO3CmKnb0CUhpRSlGgVTUoBaBZHQJwvZBeHBUJ1fZQoaAZoCWgPQwhens4VpfhMQJSGlFKUaBVLzmgWR0CcMQMpgCwKdX2UKGgGaAloD0MIIO9VK1PtcUCUhpRSlGgVTVsBaBZHQJwxHZBcAzZ1fZQoaAZoCWgPQwgMeQQ3EshxQJSGlFKUaBVNRgFoFkdAnDEo8dPtUnV9lChoBmgJaA9DCOAQqtTszU1AlIaUUpRoFUvXaBZHQJwx5i8WbgF1fZQoaAZoCWgPQwg82jhi7TZyQJSGlFKUaBVNJwFoFkdAnDPULtu1nnV9lChoBmgJaA9DCJs4ud+h3DVAlIaUUpRoFUvZaBZHQJwz6zollbx1fZQoaAZoCWgPQwjXFTPCW8hyQJSGlFKUaBVNCgFoFkdAnEl5pnHvMXV9lChoBmgJaA9DCLZnlgQou3FAlIaUUpRoFU1NAWgWR0CcSi8nNPgvdX2UKGgGaAloD0MIkxywq0lAcUCUhpRSlGgVTZQBaBZHQJxKSAUcn3N1fZQoaAZoCWgPQwhIMqt3uC1wQJSGlFKUaBVNTwFoFkdAnEpHrdFfA3V9lChoBmgJaA9DCFX2XRF8X29AlIaUUpRoFU05AWgWR0CcSrSsKb8WdX2UKGgGaAloD0MIvK/KhcppUECUhpRSlGgVS8poFkdAnErhpHqeLHV9lChoBmgJaA9DCM/ZAkLrGG5AlIaUUpRoFU00AWgWR0CcSvL/CIk7dX2UKGgGaAloD0MIuYrFb4pNcECUhpRSlGgVTTcBaBZHQJxNwInjQzF1fZQoaAZoCWgPQwh3acNhqVNyQJSGlFKUaBVNKgFoFkdAnE89FOO803V9lChoBmgJaA9DCKeRlspbx21AlIaUUpRoFU1pAWgWR0CcT4x1gYxddX2UKGgGaAloD0MI22ysxDwDckCUhpRSlGgVTSoBaBZHQJxSJsTFl051fZQoaAZoCWgPQwjw3eaNE4pvQJSGlFKUaBVNOQFoFkdAnFKzIRywOnV9lChoBmgJaA9DCApmTMEaPz5AlIaUUpRoFUvaaBZHQJxT3tv4ubt1fZQoaAZoCWgPQwiaQXxgh/hwQJSGlFKUaBVNVwFoFkdAnFRlwo9cKXV9lChoBmgJaA9DCDeMguAxBnFAlIaUUpRoFU0lAWgWR0CcViJT2nKodX2UKGgGaAloD0MI5Pih0kjJckCUhpRSlGgVTR0BaBZHQJxWuKpDNQl1fZQoaAZoCWgPQwht5pDUwiJxQJSGlFKUaBVNFQFoFkdAnFcS1NQCS3V9lChoBmgJaA9DCBuciH4tJXFAlIaUUpRoFU1AAWgWR0CcVzoa1kUcdX2UKGgGaAloD0MIuHNhpFcCcUCUhpRSlGgVTSEBaBZHQJxXTtBv73x1fZQoaAZoCWgPQwhBZmfRO9lBQJSGlFKUaBVL2WgWR0CcV4JyQxN7dX2UKGgGaAloD0MIbXU5JaAkbkCUhpRSlGgVTTYBaBZHQJxXnJGOMl11fZQoaAZoCWgPQwj7k/jcCXZJQJSGlFKUaBVLlGgWR0CcWD0MPSUkdX2UKGgGaAloD0MIOkGbHD53cECUhpRSlGgVTWEBaBZHQJxYXdN34bl1fZQoaAZoCWgPQwjsUbgeRa9xQJSGlFKUaBVNTAFoFkdAnFizs2NvO3V9lChoBmgJaA9DCH+kiAwrUG9AlIaUUpRoFU3VAWgWR0CcWX61b7j1dX2UKGgGaAloD0MIbtxifi6qckCUhpRSlGgVTSgBaBZHQJxam2MKkVN1fZQoaAZoCWgPQwgSonxBS+5wQJSGlFKUaBVNLQFoFkdAnFynqiXY2HV9lChoBmgJaA9DCDGale1DMElAlIaUUpRoFUvDaBZHQJxc81FYuCh1fZQoaAZoCWgPQwhZwARu3aNwQJSGlFKUaBVNiAFoFkdAnF1L9ETg23V9lChoBmgJaA9DCAQDCB9KKDBAlIaUUpRoFUvwaBZHQJxdmeK8+Rp1fZQoaAZoCWgPQwg83uS3aD5yQJSGlFKUaBVNQAFoFkdAnF4bWZqmCXV9lChoBmgJaA9DCBefAmC8TXNAlIaUUpRoFU1BAWgWR0CcXnl54W1udX2UKGgGaAloD0MI4zjwavnockCUhpRSlGgVS/toFkdAnF63zxwyZnV9lChoBmgJaA9DCDsah/qd63FAlIaUUpRoFU0gAWgWR0CcX46z3RG+dX2UKGgGaAloD0MI68VQTvQNcECUhpRSlGgVTSwBaBZHQJxf/BBRhtt1fZQoaAZoCWgPQwjnUIaqGBNuQJSGlFKUaBVNHQFoFkdAnGB6XfIjnnV9lChoBmgJaA9DCKXbErlgGnBAlIaUUpRoFU1GAWgWR0CcYIH5JsfrdX2UKGgGaAloD0MI3WETmbn0bECUhpRSlGgVTXQBaBZHQJxhCnR9gF51fZQoaAZoCWgPQwiX4T/dQPNwQJSGlFKUaBVNOAFoFkdAnGGQZ0jkdXV9lChoBmgJaA9DCI0ngjjPTnBAlIaUUpRoFU1lAWgWR0CcYmTNt65YdX2UKGgGaAloD0MI2SWqtwaDUkCUhpRSlGgVS+RoFkdAnGM1YyO7x3V9lChoBmgJaA9DCK8FvTeGnnBAlIaUUpRoFU0wAWgWR0CcY2KAavRrdX2UKGgGaAloD0MII/YJoJjncECUhpRSlGgVTWgBaBZHQJxjuh+OOsF1fZQoaAZoCWgPQwgX9Unu8D5yQJSGlFKUaBVNBAFoFkdAnGSgWepXIXV9lChoBmgJaA9DCGQe+YOBHW5AlIaUUpRoFU06AWgWR0CcZrjvuw5edX2UKGgGaAloD0MIqnzPSASmbkCUhpRSlGgVTSIBaBZHQJxmyyWzF/B1fZQoaAZoCWgPQwi3m+CbpqVvQJSGlFKUaBVNTwFoFkdAnGbURjBl+XV9lChoBmgJaA9DCPATB9AvYnFAlIaUUpRoFU0AAWgWR0CcZt3vQWvbdX2UKGgGaAloD0MIVcGopM4Db0CUhpRSlGgVTUcBaBZHQJxniSQo1DV1fZQoaAZoCWgPQwgzFeKRuAdxQJSGlFKUaBVNMQFoFkdAnGjKz7di2HV9lChoBmgJaA9DCM6MfjQcb3FAlIaUUpRoFU0wAWgWR0CcaWjps41hdX2UKGgGaAloD0MIAFeyY2PYcUCUhpRSlGgVTQYBaBZHQJxpe1mapgl1fZQoaAZoCWgPQwgr+G2I8W9vQJSGlFKUaBVNcQFoFkdAnGmYLPUrkXV9lChoBmgJaA9DCH/Bbth2knJAlIaUUpRoFU0mAWgWR0CcadCuEEkjdX2UKGgGaAloD0MI1hnfF5cDUUCUhpRSlGgVS8RoFkdAnGn5Mtbs4XV9lChoBmgJaA9DCC+mme511kJAlIaUUpRoFUvdaBZHQJxqUl4TsY51fZQoaAZoCWgPQwiWBn5Uw2xyQJSGlFKUaBVNAQFoFkdAnGpO+7Dl5nVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 252,
+    "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
+}

first try/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae64d6d6dab1aa536e040ac3c5fb3411006821381cc9b7be79b52020321afd2
+size 87929

first try/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7c748b72812a3e02722ec8617f91f8754d7ea8b8d5100a9938c7c3ddd10f99
+size 43393

first try/pytorch_variables.pth

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

first try/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

results.json

@@ -0,0 +1 @@
+{"mean_reward": 263.14072094344317, "std_reward": 16.18700730878561, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-10T11:34:53.471185"}