Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 252.08 +/- 36.76
+      value: 224.55 +/- 71.21
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +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 0x000002CCD0FBF0D0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002CCD0FBF160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002CCD0FBF1F0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002CCD0FBF280>", "_build": "<function ActorCriticPolicy._build at 0x000002CCD0FBF310>", "forward": "<function ActorCriticPolicy.forward at 0x000002CCD0FBF3A0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002CCD0FBF430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002CCD0FBF4C0>", "_predict": "<function ActorCriticPolicy._predict at 0x000002CCD0FBF550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002CCD0FBF5E0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002CCD0FBF670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002CCD0FBF700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002CCD0D8FE80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689669280976175800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHMzLT439OI+N7QIvvJyfL67LI081ECevQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.00044800000000000395, "_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": 3908, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.9.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.21.0"}}
+{"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 0x000001F168B94940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001F168B949D0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001F168B94A60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001F168B94AF0>", "_build": "<function ActorCriticPolicy._build at 0x000001F168B94B80>", "forward": "<function ActorCriticPolicy.forward at 0x000001F168B94C10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001F168B94CA0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001F168B94D30>", "_predict": "<function ActorCriticPolicy._predict at 0x000001F168B94DC0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001F168B94E50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001F168B94EE0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001F168B94F70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001F168980D80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689669280976175800, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHMzLT439OI+N7QIvvJyfL67LI081ECevQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.00044800000000000395, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVPQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHBpYOpbUw2MAWyUTVMBjAF0lEdAnFV221D0DnV9lChoBkdAcWqb1yvLYGgHTScBaAhHQJxZ0SYgJTl1fZQoaAZHQG8f9sabWmRoB00nAWgIR0CcXJAGB4D+dX2UKGgGR0BwV0OqebuuaAdNIwFoCEdAnF7h8pkPMHV9lChoBkdAcAJsbNr0rmgHTT4BaAhHQJxhPMMZxaR1fZQoaAZHQG72ukDZDiRoB00nAWgIR0CcZRC5EtuldX2UKGgGR0Bxr72xptaZaAdNHQFoCEdAnGc/07KaHHV9lChoBkdAcdQ1HOKO1mgHTSUBaAhHQJxphSHdoFp1fZQoaAZHQHHZP779AHFoB006AWgIR0CcbYAksz2wdX2UKGgGR0ByPlEWqLjxaAdNQAFoCEdAnHAd1+y7gHV9lChoBkdAcAPdxyXD32gHTTMBaAhHQJxyuGxlg+h1fZQoaAZHQDVqJJoTPB1oB0vsaAhHQJx0qREF4cF1fZQoaAZHQG/A2/zreIloB00eAWgIR0CceGiNsFdLdX2UKGgGR0Buv83ZPEbYaAdNHgFoCEdAnHqUl7dBSnV9lChoBkdAb6VZ4fOlf2gHTTsBaAhHQJx8+flIVdp1fZQoaAZHQEXL6eGwiaBoB00AAWgIR0CcgHr9l2/0dX2UKGgGR8A7xjpLVWjoaAdL92gIR0Ccgm6z3RG+dX2UKGgGR0ByTZtl7MPjaAdNQwFoCEdAnIT/Fm4Aj3V9lChoBkdAcTL4BmwqzGgHTSsBaAhHQJyHeXD3ueB1fZQoaAZHQHHTFk1/DtRoB01WAWgIR0Cci7PPLPlddX2UKGgGR0BwAKfqX4TLaAdNLAFoCEdAnI43C9AX23V9lChoBkdAa2qE384xUWgHTR8BaAhHQJyQoo/iYLN1fZQoaAZHQHANH++/QBxoB01hAWgIR0CclQUT+NtJdX2UKGgGR0BxedZvDP4VaAdNBgFoCEdAnJcFE7W/anV9lChoBkdAcOs4qwyIpGgHTRMBaAhHQJyZvWVeKKp1fZQoaAZHQG9OrNwBHTZoB00uAWgIR0CcnJ6LOzIFdX2UKGgGR0BxhmG9HtngaAdNIgFoCEdAnKD+jqOcUnV9lChoBkdAcHa7lJYkmmgHTUABaAhHQJyjOPluFYd1fZQoaAZHQHDL23Sa3JBoB00vAWgIR0CcpUtnPE88dX2UKGgGR0BvMpUHY6GQaAdNNAFoCEdAnKg8Vk+X7nV9lChoBkdAMlSSNfgJkWgHS/NoCEdAnKmai0v4/XV9lChoBkdAcTZzTF2mpGgHTRABaAhHQJyryKDTSb91fZQoaAZHQG8UlKkEcKhoB007AWgIR0CcrpJ+DvmYdX2UKGgGR0Bv4Z5s0pEyaAdNTwFoCEdAnLMHE/B3zXV9lChoBkdAbCuD3/Pw/mgHTUIBaAhHQJy1wL9deIF1fZQoaAZHQG8tQ7LdN35oB00zAWgIR0Cct8w+dK/VdX2UKGgGR0BwwWvzOHFhaAdNFAFoCEdAnLqGiQDFInV9lChoBkdAbj0vJRwZO2gHTScBaAhHQJy8P9wWFex1fZQoaAZHQG6TAzguRLdoB00LAWgIR0Ccva5zYEntdX2UKGgGR0BsuPKB/ZuiaAdNJQFoCEdAnL87wz+FUXV9lChoBkdAchtZJCjUNWgHTUIBaAhHQJzCEGKQ7tB1fZQoaAZHQHEDrSeAd4poB00lAWgIR0Ccw6j2Bas7dX2UKGgGR0BuRYBtDUmVaAdNYQFoCEdAnMWfvnbItHV9lChoBkdAbefa9K28ZmgHTSICaAhHQJzJv0SRKYl1fZQoaAZHQEDUh0yP+4toB0u2aAhHQJzK0bZOBUd1fZQoaAZHQHIN+xB3RohoB01BAWgIR0CczK3fAKv3dX2UKGgGR0Bw58eeWfK7aAdNJQFoCEdAnM9kLUkOZ3V9lChoBkdAcL4/336AOWgHTSQBaAhHQJzRIewLVnV1fZQoaAZHQG5qzviLl3hoB00gAWgIR0Cc0tgxrSE2dX2UKGgGR0Bwb8fHPu5SaAdNOAFoCEdAnNYlRLsa9HV9lChoBkdAceTSDAaegGgHTUgBaAhHQJzYgemvW6N1fZQoaAZHQGeK0Bfa6BloB01CAmgIR0Cc3OqBEroXdX2UKGgGR0BsMIlMRHwxaAdNNAFoCEdAnN6pm7J4jnV9lChoBkdAcE4hX8wYcmgHTUYBaAhHQJzggKXv6TJ1fZQoaAZHQG05tI065oZoB006AWgIR0Cc4kSYPXkHdX2UKGgGR0BwmDU6PsAvaAdNEgFoCEdAnOTts3yZr3V9lChoBkdAcVtngpBomGgHTVABaAhHQJzm0g4ffXR1fZQoaAZHQHDPUXpGFzxoB00yAWgIR0Cc6I1y/9HddX2UKGgGR0Buvd5Y5ksjaAdNLgFoCEdAnOwGRvFWGXV9lChoBkdAbusrc0tRN2gHTSABaAhHQJzuPl6qsEJ1fZQoaAZHQGuflLvkRz1oB01BAWgIR0Cc8P3cpLEldX2UKGgGR0BwWgM1CPZJaAdNLwFoCEdAnPV62WpqAXV9lChoBkdAcxgG/N7jUGgHTTUBaAhHQJz4fqgRK6F1fZQoaAZHQHEg4xDb8FZoB00RAWgIR0Cc+tYvWYnfdX2UKGgGR0Bu1+bZvkzXaAdNKgFoCEdAnP1TG5tm+XV9lChoBkdAcKnoWHk92WgHTScBaAhHQJ0B8tmL9/B1fZQoaAZHQG8VhEjPfKpoB00nAWgIR0CdBKUHIIWydX2UKGgGR0ByRGjvd/KAaAdNNQFoCEdAnQeEVJtix3V9lChoBkdAcC/xmkFfRmgHTS0BaAhHQJ0MEqpcX3x1fZQoaAZHQEVSFNcnmaJoB0vaaAhHQJ0OM3gk1Mx1fZQoaAZHQHHbg5Jbt7doB01KAWgIR0CdEXgTAWSEdX2UKGgGR0BwBh/CqIacaAdNMgFoCEdAnRQ2hZha1XV9lChoBkdAcV1PtD2JzmgHTR8BaAhHQJ0YlWRzRx91fZQoaAZHQGycGJWNm19oB01EAWgIR0CdG7adc0LudX2UKGgGR0BxPvBpHqeLaAdNWwFoCEdAnR9PMGHHm3V9lChoBkdAcFKX9BKL9GgHTSoBaAhHQJ0jp3os7Mh1fZQoaAZHQHAvmNBF/hFoB00mAWgIR0CdJktSAH3UdX2UKGgGR0BwQ2/O+qR2aAdNCQFoCEdAnSjIPsiSq3V9lChoBkdAcI1aw2VE/mgHTUIBaAhHQJ0r1prULD11fZQoaAZHQHFoAKrq+rVoB00/AWgIR0CdMGTPBzmwdX2UKGgGR0BH9gGr0aqCaAdL5mgIR0CdMo7LMcIadX2UKGgGR0BxE+cWj45+aAdNLgFoCEdAnTVmn0kGA3V9lChoBkdAcIEc/MW43GgHTTcBaAhHQJ06Xg5zYEp1fZQoaAZHQHG71inYQJ5oB00sAWgIR0CdPSdB0ITodX2UKGgGR0BwSNn7HhjwaAdNGQFoCEdAnT+vcvduYXV9lChoBkdAbyc2mYSg5GgHTREBaAhHQJ1CLYoRZlp1fZQoaAZHQEqkunuRcNZoB0vmaAhHQJ1GCJ1q33J1fZQoaAZHQHIB8p5NXYFoB00fAWgIR0CdSIy1NQCTdX2UKGgGR0Bvm8T6BRQ8aAdNHgFoCEdAnUsDcynDSHV9lChoBkdAcOv2KEWZZ2gHTSoBaAhHQJ1O3Ikqto11fZQoaAZHQHCOcQqZtvZoB00lAWgIR0CdUOKuSwGGdX2UKGgGR0BvOB9Aood/aAdNGQFoCEdAnVKY/3WWhXV9lChoBkdAbPFwd8zAOGgHTRIBaAhHQJ1UQfT1CgN1fZQoaAZHQHENnQyAQQNoB00PAWgIR0CdVvZK3/gjdX2UKGgGR0BxN1xkupS8aAdNFgFoCEdAnViS9qUNa3V9lChoBkdAcWBmLLpzLmgHTU4BaAhHQJ1adkqc3ER1fZQoaAZHQHCJc32mHgxoB00tAWgIR0CdXCh3qzJIdX2UKGgGR0BtQokcCHRDaAdNNgFoCEdAnV8DkU9IPXV9lChoBkdAcMiqBVdX1mgHTTkBaAhHQJ1gxRqGlAN1fZQoaAZHQGtBOBczImxoB00XAWgIR0CdYqX8wYcedWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.9.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.21.0"}}

models/ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28fb8c9f76099c04ab24eb361be6649001254dd436cc60602879ed5410f216c
+oid sha256:1fad615644332c1fa52eb8487cf756a51e9b4a59062c82b714318b79146352be
 size 146066

models/ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x000002CCD0FBF0D0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002CCD0FBF160>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002CCD0FBF1F0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002CCD0FBF280>",
-        "_build": "<function ActorCriticPolicy._build at 0x000002CCD0FBF310>",
-        "forward": "<function ActorCriticPolicy.forward at 0x000002CCD0FBF3A0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002CCD0FBF430>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002CCD0FBF4C0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x000002CCD0FBF550>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002CCD0FBF5E0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002CCD0FBF670>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002CCD0FBF700>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000001F168B94940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001F168B949D0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001F168B94A60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001F168B94AF0>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001F168B94B80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001F168B94C10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001F168B94CA0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001F168B94D30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001F168B94DC0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001F168B94E50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001F168B94EE0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001F168B94F70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000002CCD0D8FE80>"
+        "_abc_impl": "<_abc._abc_data object at 0x000001F168980D80>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 252.0808846, "std_reward": 36.76354454898942, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-18T15:53:18.604558"}
+{"mean_reward": 224.5500544, "std_reward": 71.21214700370247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-18T17:17:35.752781"}