Update

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 250.96 +/- 40.23
+      value: 249.18 +/- 44.71
       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 0x7cab004dc790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cab004dc820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cab004dc8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cab004dc940>", "_build": "<function ActorCriticPolicy._build at 0x7cab004dc9d0>", "forward": "<function ActorCriticPolicy.forward at 0x7cab004dca60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cab004dcaf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cab004dcb80>", "_predict": "<function ActorCriticPolicy._predict at 0x7cab004dcc10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cab004dcca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cab004dcd30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cab004dcdc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cab0046b400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1725206545704425960, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABrh5713Rpg/zl8wvjf73r4GMRq+MBbZvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:": "gAWVQQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG5JR+KCQLiMAWyUTRkBjAF0lEdAorn5vNu+AXV9lChoBkdAbmCf29L6DWgHTSkBaAhHQKK76i48U211fZQoaAZHQHL0YyKvV3FoB00HAWgIR0CivM6OYIBzdX2UKGgGR0ByzdSFXaJzaAdNPQFoCEdAor3jgVGkOHV9lChoBkdAcTZKGL1mJ2gHTTMBaAhHQKK/hv0h/y51fZQoaAZHQHHP2CAc1fpoB01UAWgIR0CiwLCPZIxydX2UKGgGR0BtntFOO802aAdNLgFoCEdAosG8IeHSGHV9lChoBkdAWT3SRbKRuGgHTegDaAhHQKLGjTGYKIB1fZQoaAZHQHC28y31BdFoB004AWgIR0Cix6uH31zydX2UKGgGR0BwXi3G4qgAaAdNdQFoCEdAosmsJWvKU3V9lChoBkdAbgl4rSVnmWgHTSgBaAhHQKLKvGPPszF1fZQoaAZHQGuEuJ1q33JoB00wAWgIR0Ciy9TyauwHdX2UKGgGR0BxoWiWVu76aAdNJwFoCEdAos1+zIFNcnV9lChoBkdASxo+IMz/ImgHS+JoCEdAos47XBguy3V9lChoBkdAb8qECeVcEGgHTS4BaAhHQKLPi0waisZ1fZQoaAZHQHDb6P4mCy1oB00QAWgIR0Ci0MMyJsO5dX2UKGgGR0BxqhJ4B3iaaAdNcAFoCEdAotN1tKqXGHV9lChoBkdAbQaHWSU1RGgHTTMBaAhHQKLUsOwPiDN1fZQoaAZHQG+1GWdEsrdoB01QAWgIR0Ci1d72+PBBdX2UKGgGR0ByCcClrM1TaAdNXAFoCEdAote4qZtvXXV9lChoBkdAcC/1UVBUrGgHTTYBaAhHQKLY2ORT0g91fZQoaAZHQG8/Ek0Jng5oB01FAWgIR0Ci2ffl6qsEdX2UKGgGR0Bv8dVPva11aAdNKAFoCEdAotujtG/etXV9lChoBkdAb4WPpY9xImgHTTcBaAhHQKLcyARTS9d1fZQoaAZHQHE/5Gax5cFoB002AWgIR0Ci3fDlPrOadX2UKGgGR0Bu1ps2vStvaAdNMwFoCEdAot+mB19v0nV9lChoBkdAb/d3/Pw/gWgHTUMBaAhHQKLgyjUNKAd1fZQoaAZHQHHX7ThHbypoB00rAWgIR0Ci4dBhQWN4dX2UKGgGR0BwJose4kNXaAdNQgFoCEdAouORhBqsVHV9lChoBkdAbIS3ocJdB2gHTToBaAhHQKLkrvXK8th1fZQoaAZHQHGW+pS75EdoB00xAWgIR0Ci5cn4GlhxdX2UKGgGR0BwKuNCJGe+aAdNSQFoCEdAoub0IkZ75XV9lChoBkdAbaCssg+yJWgHTTIBaAhHQKLo4ab4Ju51fZQoaAZHQHDw8ibDuShoB00lAWgIR0Ci6iBysCDFdX2UKGgGR0BwKLzND+iraAdNRgFoCEdAouvHVurIYHV9lChoBkdAcUu9OARTTGgHTUIBaAhHQKLt4tVaOgh1fZQoaAZHQG1lgccU/OdoB01CAWgIR0Ci7v4FJQLvdX2UKGgGR0BvKnxDst03aAdNIQFoCEdAou/4/qxC6nV9lChoBkdAcPzlWwNb1WgHTT0BaAhHQKLxuGC7K7t1fZQoaAZHQFV7ppeu3c5oB03oA2gIR0Ci93oouwotdX2UKGgGR0Bw0OVqveP8aAdNawFoCEdAovjdcOby6XV9lChoBkdAbEeVQhwEQ2gHTSEBaAhHQKL54RYA80V1fZQoaAZHQGx9SLAHmihoB00yAWgIR0Ci+vnoxHoYdX2UKGgGR0BwUUJSiudPaAdNHwFoCEdAovyazXz19XV9lChoBkdAbG1y7PIGQmgHTT4BaAhHQKL9wAfdRBN1fZQoaAZHQHFjm+j/MntoB00lAWgIR0Ci/sC2MKkVdX2UKGgGR0BxsFBZ6lchaAdNXwFoCEdAowCMupS75HV9lChoBkdAbm9wLE1l5GgHTUcBaAhHQKMB8s/6frd1fZQoaAZHQE8XXyRSxaBoB0vdaAhHQKMC4Jmdy1h1fZQoaAZHQHJvpgCwKShoB008AWgIR0CjBTz3h4t6dX2UKGgGR0BxysElme18aAdNNQFoCEdAowaS/O+qR3V9lChoBkdAcSRW2w3YMGgHTTgBaAhHQKMHsAd4mkZ1fZQoaAZHQHG7acmShaloB00yAWgIR0CjCNLzGxUvdX2UKGgGR0Bu44ZGax5caAdNQgFoCEdAowqYTK1XvHV9lChoBkdAa+OcH4XXRWgHTTgBaAhHQKMLuTnJT2p1fZQoaAZHQHHeDbWVeKNoB01ZAWgIR0CjDOgbp/wzdX2UKGgGR0Bq95uuRs/IaAdNcwFoCEdAow7y8jAzpHV9lChoBkdAcE0aESM982gHTTcBaAhHQKMQB8v24/h1fZQoaAZHQG96xISUTtdoB007AWgIR0CjESLWiDdydX2UKGgGR0BwTKGcnVoYaAdNMwFoCEdAoxLPwG4ZuXV9lChoBkdAbWIJCSidrmgHTUMBaAhHQKMT9BVuJk51fZQoaAZHQG6A4gA6uGNoB00/AWgIR0CjFRB5gPVedX2UKGgGR0Bwaq8UVSGbaAdNIQFoCEdAoxaqm8/Uv3V9lChoBkdAbn7yQPqcE2gHTVABaAhHQKMX6C4jKPp1fZQoaAZHQHJoxsEaESNoB01FAWgIR0CjGRBhYvFndX2UKGgGR0BygkdGRV6vaAdNQgFoCEdAoxstWwNb1XV9lChoBkdAbUi1w5vLo2gHTU8BaAhHQKMcuTaCcwx1fZQoaAZHQG+aAxi5NGpoB02YAWgIR0CjHt+qrBCVdX2UKGgGR0Bxb6dAgPmQaAdNdgJoCEdAoyH6SvC/GnV9lChoBkdAbud0nPVurWgHTWkBaAhHQKMjUt9QXRB1fZQoaAZHQHDA3uuzQeFoB00xAWgIR0CjJPjYI0IkdX2UKGgGR0Bw/HqC6H0saAdNSQFoCEdAoyYoW3z+WHV9lChoBkdAcanr92ovSWgHTSYCaAhHQKMoGAOrhit1fZQoaAZHQG0cpn6Eal1oB009AWgIR0CjKc8J2MbWdX2UKGgGR0Bwbl9y925haAdNIAFoCEdAoyrR93KSxXV9lChoBkdAcOjmj0th/mgHTSYBaAhHQKMr2MRYigV1fZQoaAZHQGQECoKlYU5oB03oA2gIR0CjMPdNet0WdX2UKGgGR0BxOZXDFZPmaAdNSwFoCEdAozK+LpA2RHV9lChoBkdAch/ElVtGeGgHTYcCaAhHQKM2CZtvXK91fZQoaAZHQG5B+pOvdM1oB006AWgIR0CjOB+UY8+zdX2UKGgGR0BvOw/1QIldaAdNEQJoCEdAozoz90ihWnV9lChoBkdAcFkB9Tgl4WgHTR0BaAhHQKM7KXCTEBN1fZQoaAZHQHDWM7IT4+NoB01DAWgIR0CjPNktVaOhdX2UKGgGR0BtWVNDc/MXaAdNUAFoCEdAoz4TzmOlwnV9lChoBkdAbmXcTrVvuWgHTWMBaAhHQKM/VYQrc0t1fZQoaAZHQHA7im2sq8VoB01bAWgIR0CjQSiCBf8edX2UKGgGR0BxlS1jRUm2aAdNRQFoCEdAo0JiLOzIFXV9lChoBkdAY6khaC+UQmgHTegDaAhHQKNHAGs3hn91fZQoaAZHQHDiwMH8jzJoB00qAWgIR0CjSAoOYplSdX2UKGgGR0BxLpVOsT37aAdNIAFoCEdAo0kHOQhfSnV9lChoBkdAbfKctGus92gHTSEBaAhHQKNKmrZJ04l1fZQoaAZHQG+zs+FDfFdoB00iAWgIR0CjS7c7IT4+dX2UKGgGR0BwZ4NCqp97aAdN0gFoCEdAo07fBHkLhXV9lChoBkdAcT0S5y2hI2gHTSQBaAhHQKNQOzXz19R1fZQoaAZHQHHrU9QoCuFoB001AWgIR0CjUUDTKDChdX2UKGgGR0Bv+Hrv9cbBaAdNCQFoCEdAo1Io//vOQnV9lChoBkdARKDbUPQOWmgHS95oCEdAo1NyCBf8dnV9lChoBkdAcKcvkBCD3GgHTUIBaAhHQKNUjehPCVN1fZQoaAZHQHB87XYlIEtoB007AWgIR0CjVaTHjp9rdX2UKGgGR0Bvj1V94NZvaAdNAQFoCEdAo1aQwudwvXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.009, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7b93a637c940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b93a637c9d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b93a637ca60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b93a637caf0>", "_build": "<function ActorCriticPolicy._build at 0x7b93a637cb80>", "forward": "<function ActorCriticPolicy.forward at 0x7b93a637cc10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b93a637cca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b93a637cd30>", "_predict": "<function ActorCriticPolicy._predict at 0x7b93a637cdc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b93a637ce50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b93a637cee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b93a637cf70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b93a6514540>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1725769484412443954, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM0EKb3HPqM/zEWlvnPB777b8Bu9OaIVvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96903534219b57730cb0567006a8ecd799a6f6a2eaddfd214443d6fd93d1067
-size 147427
+oid sha256:31427d5088f4dcc6ef05b2fecb38e629292b28da7e85de553bd3f7781c45949f
+size 142775

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 0x7cab004dc790>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cab004dc820>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cab004dc8b0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cab004dc940>",
-        "_build": "<function ActorCriticPolicy._build at 0x7cab004dc9d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7cab004dca60>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cab004dcaf0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cab004dcb80>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7cab004dcc10>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cab004dcca0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cab004dcd30>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cab004dcdc0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b93a637c940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b93a637c9d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b93a637ca60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b93a637caf0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b93a637cb80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b93a637cc10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b93a637cca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b93a637cd30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b93a637cdc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b93a637ce50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b93a637cee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b93a637cf70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cab0046b400>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b93a6514540>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1725206545704425960,
+    "start_time": 1725769484412443954,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABrh5713Rpg/zl8wvjf73r4GMRq+MBbZvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM0EKb3HPqM/zEWlvnPB777b8Bu9OaIVvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -80,7 +80,7 @@
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
-    "ent_coef": 0.009,
+    "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5331cf184bbf46ed81238c145721deca55f88564ee307b584e98956c1487ebe2
-size 88362
+oid sha256:f2245ebd980bda1cef64884dc33a73af10e2ddbe19044c78cfd8a863429f2a09
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e04ca49578ad2160e5fd41f90c2a7bd3782bfbcafe664ae42416a90cdb7b022a
-size 43762
+oid sha256:b94f153e0c518e2a864f0687b37c4ce37241f8dae1412de5a6a4574ba796150f
+size 43634

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.4.0+cu121
-- GPU Enabled: True
+- GPU Enabled: False
 - Numpy: 1.26.4
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1

results.json

@@ -1 +1 @@
-{"mean_reward": 250.96067631417318, "std_reward": 40.229102497882614, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-01T16:48:01.183582"}
+{"mean_reward": 249.17909567329306, "std_reward": 44.713613323153055, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-08T05:06:39.417958"}