Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 263.93 +/- 14.36
+      value: 272.44 +/- 18.06
       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 0x78ebfb2bbd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ebfb2bbdc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ebfb2bbe50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ebfb2bbee0>", "_build": "<function ActorCriticPolicy._build at 0x78ebfb2bbf70>", "forward": "<function ActorCriticPolicy.forward at 0x78ebfb2bf040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ebfb2bf0d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ebfb2bf160>", "_predict": "<function ActorCriticPolicy._predict at 0x78ebfb2bf1f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ebfb2bf280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ebfb2bf310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ebfb2bf3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78ebfb8061c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1759330597446176188, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAQ/M9NK4FPngnXL5iIbC+Fr+ZvcY767wAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "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": "Linux-6.14.0-28-generic-x86_64-with-glibc2.39 # 28~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul 25 10:47:01 UTC 2", "Python": "3.9.20", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.8.0+cu128", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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 0x786fb6737d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fb6737dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fb6737e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fb6737ee0>", "_build": "<function ActorCriticPolicy._build at 0x786fb6737f70>", "forward": "<function ActorCriticPolicy.forward at 0x786fb673a040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fb673a0d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fb673a160>", "_predict": "<function ActorCriticPolicy._predict at 0x786fb673a1f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fb673a280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fb673a310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fb673a3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x786fb67389c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1759330597446176188, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAQ/M9NK4FPngnXL5iIbC+Fr+ZvcY767wAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_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:": "gAWVGgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHDsO18b70qMAWyUS/6MAXSUR0CAZXDm8ujAdX2UKGgGR0ByICF7D2rXaAdNMQFoCEdAgGaKWTot+XV9lChoBkdAcvgUvPC2t2gHTRMBaAhHQIBnhhYvFm51fZQoaAZHQHFN3irDIiloB0v2aAhHQIBpJqfvnbJ1fZQoaAZHQHBUyHymQ8xoB00YAWgIR0CAaifcvduYdX2UKGgGR0BuAVPUKArhaAdL4mgIR0CAavZGKAJ+dX2UKGgGR0BxDI2Kl54XaAdL7WgIR0CAa881XNkfdX2UKGgGR0BtRG3x4IKMaAdL72gIR0CAbKoegctHdX2UKGgGR0Bw7Hu0CzTnaAdNDwFoCEdAgG5jrAxi5XV9lChoBkdAcO8/bj94vGgHS95oCEdAgG8vTG5tnHV9lChoBkdAau6iO/+Kj2gHTRsBaAhHQIBwMsJ6Y3N1fZQoaAZHQG1g4aHbh3toB00UAWgIR0CAcfIoVmBfdX2UKGgGR0BwmN6+nIhhaAdL1WgIR0CAcrQv6CUYdX2UKGgGR0BwRBOARTS9aAdL+mgIR0CAc5ifg75mdX2UKGgGR0BtQdyzXz19aAdL9mgIR0CAdHqynk1edX2UKGgGR0Bwkml41P30aAdL+mgIR0CAdV8qnWJ8dX2UKGgGR0BwTSlO45LiaAdL8GgIR0CAdvs+FDfFdX2UKGgGR0BxepSde6ZqaAdNHwFoCEdAgHgDSXt0FXV9lChoBkdAYL+VN5+pfmgHTegDaAhHQIB8dYEGJN11fZQoaAZHQHIiQKOT7l9oB00WAWgIR0CAfXKeTV2BdX2UKGgGR0Bxc6K508vFaAdNDwFoCEdAgH5pBgNPQHV9lChoBkdAcCpsYEW69WgHS9JoCEdAgH/wtJ4B3nV9lChoBkdAcFwDtw71ZmgHTQkBaAhHQICA4lOXVsl1fZQoaAZHQHBfGD15B1NoB0vfaAhHQICBrlT3qRl1fZQoaAZHQHBEU47zTWpoB00uAWgIR0CAgsH8CPp7dX2UKGgGR0BxClum78NyaAdL+mgIR0CAhG0CzTnadX2UKGgGR0BlF8oDxLCfaAdN6ANoCEdAgIjSNOuaF3V9lChoBkdActUO7QLNOmgHTScBaAhHQICJ37Jnxrl1fZQoaAZHQG/WIuGsV+JoB0v2aAhHQICKwH/tICl1fZQoaAZHQHH+odU83ddoB01aAWgIR0CAjMV9nbqRdX2UKGgGR0BwPT5ckdFOaAdL8GgIR0CAjaA4GUwBdX2UKGgGR0BMUafSQYDUaAdLx2gIR0CAjlZmqYJFdX2UKGgGR0BvI9D2JzkqaAdL9WgIR0CAjzbhWHUMdX2UKGgGR0BxiREAo5PuaAdNOAFoCEdAgJEQJgLJCHV9lChoBkdAYY+YE4ecQWgHTegDaAhHQICUusNlRP51fZQoaAZHQEjX3aBZpztoB0vVaAhHQICWQSg5BC51fZQoaAZHQHLbCpNsWO9oB0v4aAhHQICXJGvwEyN1fZQoaAZHQHDqSydFvydoB0v1aAhHQICYBREWqLl1fZQoaAZHQHGRDkU9IPNoB00YAWgIR0CAmQtxuKoAdX2UKGgGR0BwqXM1TBInaAdNDAFoCEdAgJrCvovBanV9lChoBkdAcThrSmZVn2gHTQEBaAhHQICbrNwBHTZ1fZQoaAZHQHCtH2RJVbRoB00HAWgIR0CAnJyc0+C9dX2UKGgGR0BvqijBVMmGaAdNLgFoCEdAgJ5yCOFQEnV9lChoBkdAYwDz1bqyGGgHTegDaAhHQICiEiMYMv11fZQoaAZHQHHDTEJjUd9oB00JAWgIR0CAo8alUIcBdX2UKGgGR0BwFsrf+CK8aAdL72gIR0CApKEidJ8OdX2UKGgGR0BxSofU4JeFaAdNAQFoCEdAgKWL3j+72HV9lChoBkdAaPvikwevIWgHTb8CaAhHQICo3GbTc7B1fZQoaAZHQHBFOdsi0OVoB00DAWgIR0CAqcmrsByTdX2UKGgGR0Bv6p4D9wWFaAdNFwFoCEdAgKrIXsPatnV9lChoBkdAb2rWMju8b2gHS+hoCEdAgKxfICEHuHV9lChoBkdAcfmQ/HHWBmgHTR8BaAhHQICtZSzgMtt1fZQoaAZHQG3amfGuLaVoB0v3aAhHQICuR1q33Ht1fZQoaAZHQHAVd5Y5ksloB0vmaAhHQICvGFajesR1fZQoaAZHQG9ois4ku6FoB00LAWgIR0CAsNAxBVuKdX2UKGgGR0Bxy1qHoHLSaAdNEgFoCEdAgLHLjYI0InV9lChoBkdAcM0SeRPoFGgHS+VoCEdAgLKc14xDcHV9lChoBkdAcRU+fRNRFmgHTQMBaAhHQICziOxSpBJ1fZQoaAZHQHLHtmlImPZoB0vsaAhHQIC1JJAdGRV1fZQoaAZHQFy/6uGKyfNoB03oA2gIR0CAuYOby6MBdX2UKGgGR0BwtBhuwX67aAdNEwFoCEdAgLp/ACW/rXV9lChoBkdAbW1cL0BfbGgHTRUBaAhHQIC7e2d/axp1fZQoaAZHQG5+WRaHKwJoB0v9aAhHQIC8YUahpQF1fZQoaAZHQDnhCZ4Oc2BoB0vFaAhHQIC92dZq20B1fZQoaAZHQHEAI0ALiMpoB01eAWgIR0CAvxqTKT0QdX2UKGgGR0BxakouwosqaAdNFwFoCEdAgMAYm9g4O3V9lChoBkdAY3Knb7CSBGgHTegDaAhHQIDEcw8GLUF1fZQoaAZHQHCjWK/EfkpoB00kAWgIR0CAxX1V5rxidX2UKGgGR0Bv9YEOiFj/aAdL+mgIR0CAxyOcUdq+dX2UKGgGR0BxKIJa7mMgaAdNBwFoCEdAgMgUTcqOLnV9lChoBkdAbgTkiliz9mgHS/ZoCEdAgMj0o8ZDRnV9lChoBkdAcR7vTgEU02gHTQoBaAhHQIDJ5vitJWh1fZQoaAZHQHBrVGCqZMNoB00QAWgIR0CAy6MIeHSGdX2UKGgGR0BwmDROUMXraAdNBAFoCEdAgMyPttygf3V9lChoBkdAcoAkj5bhWGgHTSgBaAhHQIDNngUDdQB1fZQoaAZHQG6mjtoi9qVoB0vvaAhHQIDPOg13t8h1fZQoaAZHQHCwuOOsDGNoB00SAWgIR0CA0DRekYXPdX2UKGgGR0Bxe0eU6gdwaAdNDAFoCEdAgNEm4y44InV9lChoBkdAbSHmp2ll9WgHTRIBaAhHQIDSIDA8B+51fZQoaAZHQG6slfZ26kJoB0v0aAhHQIDTv0XgtOF1fZQoaAZHQG3t5fD1oQFoB00fAWgIR0CA1MSdOIqLdX2UKGgGR0BwuYr/bTMJaAdNFwFoCEdAgNXDTz/ZNHV9lChoBkdAcmVTJyQxOGgHS/1oCEdAgNapHy3CsXV9lChoBkdAbwBRb8m8d2gHS+loCEdAgNg9joZAIXV9lChoBkdAcFwanrIHT2gHS+doCEdAgNkPvrnkk3V9lChoBkdAcOqyAQQL/mgHTU8BaAhHQIDaQTufEn91fZQoaAZHQG2lPczqKP5oB00KAWgIR0CA2zOi35N5dX2UKGgGR0BwgHjU/fO2aAdL4mgIR0CA3MP3i704dX2UKGgGR0Bw0GoxYaHcaAdNNwFoCEdAgN3f9pAUtnV9lChoBkdAcIzfeDWbw2gHS/loCEdAgN7C83++/XV9lChoBkdAcY2tFKCg9WgHTRYBaAhHQIDfwnc+JP91fZQoaAZHQHGbbuUliSdoB00UAWgIR0CA4X5GjKxLdX2UKGgGR0BxUaBFuvU0aAdL3mgIR0CA4knbZezEdX2UKGgGR0Bjpc9QoCuEaAdN6ANoCEdAgOan4Glhw3V9lChoBkdAcGy9FWn0kGgHTVsCaAhHQIDpjo0Q9Rt1fZQoaAZHQGVvs+/xlQNoB03oA2gIR0CA7SnvUjLTdX2UKGgGR0BxfYRh+fAcaAdNEwFoCEdAgO7jMeOn23V9lChoBkdAQ+zeANG3F2gHS8NoCEdAgO+XiiqQzXV9lChoBkdARGoRwqAjIWgHS7BoCEdAgPA4ht+CsnV9lChoBkdAbdPGgi/wiWgHS+5oCEdAgPER5cC5mXVlLg=="}, "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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "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": "Linux-6.14.0-33-generic-x86_64-with-glibc2.39 # 33~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 19 17:02:30 UTC 2", "Python": "3.9.20", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.8.0+cu128", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa756e2b34465e7e4b44fd2acea27623833aefa638e8925090eb1b755aba5de3
-size 148709
+oid sha256:86ab6ad1464a8f9754b18cb25e16a38a67435a1413f4930520eac7964a977896
+size 148730

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 0x78ebfb2bbd30>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ebfb2bbdc0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ebfb2bbe50>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ebfb2bbee0>",
-        "_build": "<function ActorCriticPolicy._build at 0x78ebfb2bbf70>",
-        "forward": "<function ActorCriticPolicy.forward at 0x78ebfb2bf040>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ebfb2bf0d0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ebfb2bf160>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x78ebfb2bf1f0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ebfb2bf280>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ebfb2bf310>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ebfb2bf3a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x786fb6737d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fb6737dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fb6737e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fb6737ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x786fb6737f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x786fb673a040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fb673a0d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fb673a160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x786fb673a1f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fb673a280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fb673a310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fb673a3a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78ebfb8061c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x786fb67389c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-6.14.0-28-generic-x86_64-with-glibc2.39 # 28~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Jul 25 10:47:01 UTC 2
+- OS: Linux-6.14.0-33-generic-x86_64-with-glibc2.39 # 33~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 19 17:02:30 UTC 2
 - Python: 3.9.20
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.8.0+cu128
@@ -6,3 +6,4 @@
 - Numpy: 2.0.2
 - Cloudpickle: 3.1.1
 - Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69562a6509bff095282e17e06ad113d66f7186a0e7693f3366789f720ea5cadb
-size 103654
+oid sha256:67aa88943c98cf317aa1eac60d8bdce5ca1a5c1669ad4cdf4325ef09985a2146
+size 135635

results.json

@@ -1 +1 @@
-{"mean_reward": 263.9324264999999, "std_reward": 14.360304506054112, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T17:17:58.533459"}
+{"mean_reward": 272.4364802, "std_reward": 18.055130919692903, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-30T16:58:14.472223"}