Initial Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.99 +/- 65.81
+      value: 211.69 +/- 95.47
       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 0x160111940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1601119d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x160111a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x160111af0>", "_build": "<function ActorCriticPolicy._build at 0x160111b80>", "forward": "<function ActorCriticPolicy.forward at 0x160111c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x160111ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x160111d30>", "_predict": "<function ActorCriticPolicy._predict at 0x160111dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x160111e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x160111ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x160111f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x1601131e0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 10000384, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696854675028555000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJZIwz5DFmg/4kEKP0mLXb8b2Pc9KlJXPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -3.8399999999993994e-05, "_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": 19532, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.35, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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": "macOS-13.6-arm64-arm-64bit Darwin Kernel Version 22.6.0: Fri Sep 15 13:41:28 PDT 2023; root:xnu-8796.141.3.700.8~1/RELEASE_ARM64_T6000", "Python": "3.8.10", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
+{"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 0x130551940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1305519d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x130551a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x130551af0>", "_build": "<function ActorCriticPolicy._build at 0x130551b80>", "forward": "<function ActorCriticPolicy.forward at 0x130551c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x130551ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x130551d30>", "_predict": "<function ActorCriticPolicy._predict at 0x130551dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x130551e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x130551ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x130551f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x130553240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 15001600, "_total_timesteps": 15000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696857797005591000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANo7mT17EqO6SpxMul44SDS603i6Cy1rOQAAgD8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00010666666666669933, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVJAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGPog4n4O+aMAWyUTegDjAF0lEdArkUr41xbS3V9lChoBkdAQUJF1B+nZWgHS2poCEdArkU2uzQeFXV9lChoBkdAZODNmlImPmgHTegDaAhHQK5FoAWi1zB1fZQoaAZHQGdGQ6IWP91oB03oA2gIR0CuRjHQQcxTdX2UKGgGR0BjurfR/mT1aAdN6ANoCEdArkacIu5BknV9lChoBkdAZPsmvW6K+GgHTegDaAhHQK5HOjVQQ+V1fZQoaAZHQFxV7wrlNlBoB03oA2gIR0CuR6L08NhFdX2UKGgGR0BY9WXPZ7HAaAdN6ANoCEdArkg3hqCYkXV9lChoBkdAZeA7CBPKuGgHTegDaAhHQK5IowtapxZ1fZQoaAZHQGixcu8K5TZoB03oA2gIR0CuSUSJKraNdX2UKGgGR0BLbVhLGrCFaAdLh2gIR0CuSVKiO/+LdX2UKGgGR0AoNygf2bobaAdLamgIR0CuSV23BpHqdX2UKGgGR0BdFKRyOq//aAdN6ANoCEdArknM2tMfzXV9lChoBkdAYNWqH446wWgHTegDaAhHQK5Kb1BdD6Z1fZQoaAZHQGdtyvkili1oB03oA2gIR0CuSt2dmQKbdX2UKGgGR0BK8viT+vQoaAdLaGgIR0CuSuiDdxhldX2UKGgGR0BJ2deIEbHZaAdLgWgIR0CuSvXv6TGHdX2UKGgGR0A0ONN8E3bVaAdLdWgIR0CuSzBgNPP+dX2UKGgGR0BkIxiVjZtfaAdN6ANoCEdArkuaBwuM/HV9lChoBkdAQMI9LYf4h2gHS2poCEdArkukj5bhWHV9lChoBkdAYkE7GNrCWWgHTegDaAhHQK5MNRzBAOd1fZQoaAZHQGAepg9eQdVoB03oA2gIR0CuTJ6SDAaedX2UKGgGR0BLxTK1XvH+aAdLfGgIR0CuTKvES/TLdX2UKGgGR0BcYgsK9f1IaAdN6ANoCEdArk1EBwMpgHV9lChoBkdATi2gzxgAqGgHS2ZoCEdArk1On62v0XV9lChoBkdAWvkBnzxwymgHTegDaAhHQK5NuXfIjnp1fZQoaAZHQDOvvJA+pwVoB0tsaAhHQK5NxDYywfR1fZQoaAZHQGHerL6k691oB03oA2gIR0CuTlc8TzundX2UKGgGR0AupGtITXaraAdLf2gIR0CuTmO8kD6ndX2UKGgGR0BIlbaZhKDkaAdLfmgIR0CuTnAq3EyddX2UKGgGR0BhhWAbyYoiaAdN6ANoCEdArk7egezUqnV9lChoBkdAZYoU8FINE2gHTegDaAhHQK5PgExIre91fZQoaAZHQGMndPUKArhoB03oA2gIR0CuT+pobn5jdX2UKGgGR0Bg0xZyMkyDaAdN6ANoCEdArlB9p9JBgXV9lChoBkdAWs0wpON5t2gHTegDaAhHQK5Q61Bt1p11fZQoaAZHQFr7Xd0q6OJoB03oA2gIR0CuUX9joZAIdX2UKGgGR0BmtDiXIEKWaAdN6ANoCEdArlHsv/R3NnV9lChoBkdAXn3YFqzqr2gHTegDaAhHQK5ShCE6DGt1fZQoaAZHQGZ7SElE7XBoB03oA2gIR0CuUvF7tzCDdX2UKGgGR0BjoBlMAWBSaAdN6ANoCEdArlOIF/x2CHV9lChoBkc/8t7NSqEOAmgHS3JoCEdArlOUGcFyJnV9lChoBkdAAnXfZVXFLmgHS3loCEdArlOhIz3yqnV9lChoBkdAZMwR3/xUemgHTegDaAhHQK5UD2xptaZ1fZQoaAZHQFf5aM72crloB03oA2gIR0CuVLMdkrf+dX2UKGgGR0Bkp1hy8zyjaAdN6ANoCEdArlUkiGFi8XV9lChoBkdAUQoA3kxREWgHS3NoCEdArlUxC2MKkXV9lChoBkdAZnZ5cC5mRWgHTegDaAhHQK5VyxYaHbh1fZQoaAZHQGbVSVnmJWNoB03oA2gIR0CuVjWepXIVdX2UKGgGR0Aa16AvtdAxaAdLeWgIR0CuVkGorFwUdX2UKGgGR0BZlCNbTtsvaAdN6ANoCEdArlbX7el9B3V9lChoBkdAXn0I/qxC6mgHTegDaAhHQK5XQ9JSR8t1fZQoaAZHQEdWRjBl+VloB0uFaAhHQK5XUZCOWB11fZQoaAZHQF7jbA1vVExoB03oA2gIR0CuV/JnQID6dX2UKGgGR0BmjO3pfQa8aAdN6ANoCEdArlhh7ojfN3V9lChoBkdAYCetlqagEmgHTegDaAhHQK5ZBlcyFf11fZQoaAZHQD96Dh99c8loB0traAhHQK5ZEWoFV1h1fZQoaAZHQEbASntOVPhoB0uOaAhHQK5ZIBBiTdN1fZQoaAZHQGAZ1yWAwwloB03oA2gIR0CuWY/ReC04dX2UKGgGR0A6eLJCBwuNaAdLeGgIR0CuWdIl+mWMdX2UKGgGR0BMtC8WbgCPaAdLc2gIR0CuWd4LCvX9dX2UKGgGR0BmFsX7+DODaAdN6ANoCEdArlpPN5dGAnV9lChoBkdAXG6SEDhcaGgHTegDaAhHQK5a931zySV1fZQoaAZHQGKYX7k4m1JoB03oA2gIR0CuW2c5Ke05dX2UKGgGR0BhAX9UCJXRaAdN6ANoCEdArlwL7O3UhHV9lChoBkdAZuss4ku6E2gHTegDaAhHQK5cew3YL9d1fZQoaAZHwEaC8Yht+CtoB0tsaAhHQK5chm2b5M11fZQoaAZHQEEASs8xKxtoB0uCaAhHQK5ck8tf5UN1fZQoaAZHQEwk384xUNtoB0uRaAhHQK5cowFkhA51fZQoaAZHQEVBnFo+OfdoB0t3aAhHQK5cr5hz/6x1fZQoaAZHQGZARODaoMtoB03oA2gIR0CuXVIHcDbKdX2UKGgGR0BhZc4//vORaAdN6ANoCEdArl3CZUkv9XV9lChoBkdAQgqaXrt3OmgHS2RoCEdArl3NJL/S6XV9lChoBkdAZjUWgOBlMGgHTegDaAhHQK5ebqqOtGN1fZQoaAZHQGZtTIV/MGJoB03oA2gIR0CuXuMJx//edX2UKGgGR0Bi0Ic3l0YCaAdN6ANoCEdArl+HBvaURnV9lChoBkdAZBoqaw2VFGgHTegDaAhHQK5f9f779AJ1fZQoaAZHQEZVAC4jKPpoB0t8aAhHQK5gAw7DEWJ1fZQoaAZHQDgUaP0Zm7JoB0t/aAhHQK5gECwr1/V1fZQoaAZHQF2/QC0WuYBoB03oA2gIR0CuYKkyDZlGdX2UKGgGR0BhszDO1OTJaAdN6ANoCEdArmEXyRSxaHV9lChoBkdAROMOXmeUZGgHS3ZoCEdArmEjlmvnsHV9lChoBkdAZworc0tRN2gHTegDaAhHQK5hvVinYQJ1fZQoaAZHQD0z50r9VFRoB0t9aAhHQK5hyhnJ1aJ1fZQoaAZHQGdNCUX531VoB03oA2gIR0CuYjiiAUcodX2UKGgGR0BCr305EMLGaAdLcWgIR0CuYkSa/h2odX2UKGgGR0Belz1bqyGBaAdN6ANoCEdArmLmokzGgnV9lChoBkdAZNcMWoFV1mgHTegDaAhHQK5jVfKISDh1fZQoaAZHQGBSDIaLn9xoB03oA2gIR0CuY/hKL877dX2UKGgGR0BnoLbJwKjSaAdN6ANoCEdArmRo75mAb3V9lChoBkdAYPXaXa8HwGgHTegDaAhHQK5lBuKGcnV1fZQoaAZHQGQD3Zf2K2toB03oA2gIR0CuZXSElE7XdX2UKGgGR0BmmQHLRrrPaAdN6ANoCEdArmYWfbsWwnV9lChoBkdAZt9a7EpAlmgHTegDaAhHQK5mhoQFs551fZQoaAZHQGfpE4m1IAhoB03oA2gIR0CuZy2EK3NLdX2UKGgGR0BokrZnL7oCaAdN6ANoCEdArmedi4J/onV9lChoBkdAZP7fl6qsEWgHTegDaAhHQK5oPyup0fZ1fZQoaAZHQEjVapxWDHxoB0tvaAhHQK5oSxzq8lJ1fZQoaAZHQGYp6iblRxdoB03oA2gIR0CuaLzN+so2dX2UKGgGR0BikNXko4MnaAdN6ANoCEdArmleDzyz5XV9lChoBkdAYHme05U96mgHTegDaAhHQK5pzihnJ1d1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 29300, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.99, "ent_coef": 0.02, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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": "macOS-13.6-arm64-arm-64bit Darwin Kernel Version 22.6.0: Fri Sep 15 13:41:28 PDT 2023; root:xnu-8796.141.3.700.8~1/RELEASE_ARM64_T6000", "Python": "3.8.10", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e0ec51a14bb3d14294c7ff44013c310dc0c00351c0a0267d5d1a5a329b067b
-size 146953
+oid sha256:38f921d13c77bada72f06119054996433773e5530ca150337a812e9a25451f83
+size 147045

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x160111940>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1601119d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x160111a60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x160111af0>",
-        "_build": "<function ActorCriticPolicy._build at 0x160111b80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x160111c10>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x160111ca0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x160111d30>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x160111dc0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x160111e50>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x160111ee0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x160111f70>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x130551940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1305519d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x130551a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x130551af0>",
+        "_build": "<function ActorCriticPolicy._build at 0x130551b80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x130551c10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x130551ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x130551d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x130551dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x130551e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x130551ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x130551f70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x1601131e0>"
+        "_abc_impl": "<_abc_data object at 0x130553240>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 10000384,
-    "_total_timesteps": 10000000,
+    "num_timesteps": 15001600,
+    "_total_timesteps": 15000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1696854675028555000,
+    "start_time": 1696857797005591000,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJZIwz5DFmg/4kEKP0mLXb8b2Pc9KlJXPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANo7mT17EqO6SpxMul44SDS603i6Cy1rOQAAgD8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -3.8399999999993994e-05,
+    "_current_progress_remaining": -0.00010666666666669933,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 19532,
+    "_n_updates": 29300,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -79,8 +79,8 @@
     "n_envs": 1,
     "n_steps": 2048,
     "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.35,
+    "gae_lambda": 0.99,
+    "ent_coef": 0.02,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 128,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003f6c426352f0344251d9d79fbaa3cf6774a8b08ff30c6ecc9c34d33551f8f0
+oid sha256:ed5b2c0afe7a98b6cd579d443f63ca08aeb64d067202233da4ad9005dd108dfa
 size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69cd5b4f3d21cdd8804758b6d623ee7e4386a94c84da8aad9405f3d0323d0c8
+oid sha256:5ba2cbbe975ab9484027c25a8f0e90c9ea85888bba929c707bf8fd74727d4214
 size 43634

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d10c8b5230d23c85c286f96509a779e7db3f779fcfb190eaa0a76440d4dafa4
-size 172907
+oid sha256:105d53270510ad1a65d6bb937fa21e1c8b12ba813f7f70bc230c8681578fe654
+size 159595

results.json

@@ -1 +1 @@
-{"mean_reward": -128.98952029999998, "std_reward": 65.80853873796141, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-09T09:07:42.270445"}
+{"mean_reward": 211.68535550000001, "std_reward": 95.46945438985846, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-09T10:28:12.021153"}