First try

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 199.79 +/- 97.20
+      value: 283.84 +/- 18.16
       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 0x7f69e068bac0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f69e068bb50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f69e068bbe0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f69e068bc70>", "_build": "<function ActorCriticPolicy._build at 0x7f69e068bd00>", "forward": "<function ActorCriticPolicy.forward at 0x7f69e068bd90>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f69e068be20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f69e068beb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f69e068bf40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f69e069c040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f69e069c0d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f69e069c160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f69e068df00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687962861203361809, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZHDL4mIpw/HnWlvlsQnb7br1++omIGvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:": "gAWVNwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHAaKRQrMC+MAWyUTXwBjAF0lEdAnMzhH5Jsf3V9lChoBkdAOVpHy3CsO2gHTR4BaAhHQJzQ/+m3vx91fZQoaAZHQG+gyQo1DShoB01XAWgIR0Cc011hsqJ/dX2UKGgGR0BAnUT+NtIkaAdNRwFoCEdAnNU40/GEPHV9lChoBkdAby6Eh7mdRWgHTXMBaAhHQJzYZR64Uex1fZQoaAZHQDnIhFEy+HtoB00qAWgIR0Cc2kLeQ+2WdX2UKGgGR0BtdXEuQIUraAdNVwFoCEdAnNxD/ZM+NnV9lChoBkdARvZOclPac2gHTSkBaAhHQJzfC8OCoTB1fZQoaAZHQG6O4MfA9FFoB01fAWgIR0Cc4QAT7EYPdX2UKGgGR0Bun3XCj1wpaAdNbAFoCEdAnOMF5nlGPXV9lChoBkdAOHcunMt9QWgHTSgBaAhHQJzl62OQyRB1fZQoaAZHQG+LS9mHxjJoB019AWgIR0Cc6Alb/wRXdX2UKGgGR0ByCvo3aSLZaAdNOAFoCEdAnOnTJ6po9XV9lChoBkdAa+SPp6hQFmgHTXABaAhHQJzs+rksBhh1fZQoaAZHwBjIgmqo60ZoB00WAWgIR0Cc7o+t8uzydX2UKGgGR0Bud5XQtz0ZaAdNKAFoCEdAnPA9dE9dNXV9lChoBkdAbqPWz4UN8WgHTTIBaAhHQJzyAD2alUJ1fZQoaAZHQEsUCV8kUsZoB00HAWgIR0Cc9J0zTF2ndX2UKGgGR0Br+TFdcB2faAdNXwFoCEdAnPaki6g/T3V9lChoBkdAIjR1gYxcmmgHS8JoCEdAnPfBlcyFf3V9lChoBkdAaj9NGEwnIGgHTT0BaAhHQJz63l3hXKd1fZQoaAZHQHDDibx3FDRoB00sAWgIR0Cc/Rs2eg+RdX2UKGgGR0BxEvgHeJpGaAdNxAFoCEdAnQBkRSP2f3V9lChoBkdARZqoOx0MgGgHTTYBaAhHQJ0EWk+HJtB1fZQoaAZHQEyjFYMfA9FoB00NAWgIR0CdBqfL9uP4dX2UKGgGR0A2o+Lm6oVEaAdL3GgIR0CdCI5Jbt7bdX2UKGgGR0BxQ7lU6xPgaAdNZQFoCEdAnQuNxQzk63V9lChoBkdAcXF/tIClrWgHTZEBaAhHQJ0PVi9Zid91fZQoaAZHQElnWXC0ngJoB00ZAWgIR0CdEOOsDGLldX2UKGgGR0BMr/xtpEhJaAdNOgFoCEdAnRKU1EVnEnV9lChoBkdAcAWnZCfHxWgHTZUBaAhHQJ0V/2xptaZ1fZQoaAZHQDYMIKMNtqJoB0v4aAhHQJ0XZbLU1AJ1fZQoaAZHQGz8A8B+4LFoB01FAWgIR0CdGTU70WdmdX2UKGgGR0BEmY3FUADJaAdL8mgIR0CdG55Gz8gqdX2UKGgGR0Bxb/jbSJCTaAdNWwFoCEdAnR2Mv7FbV3V9lChoBkdAbMOvPC2tuGgHTUABaAhHQJ0fW4NI9Tx1fZQoaAZHQG78aAe7tiRoB01KAWgIR0CdImQm/nGLdX2UKGgGRz/2PfsNUfgaaAdNDQFoCEdAnSQRfa6BiHV9lChoBkdAcNc7ngYP5GgHTTMBaAhHQJ0l8bfgrH51fZQoaAZHQDrCpOvdM0xoB0vsaAhHQJ0nXQKKHfx1fZQoaAZHQENQOMl1KXhoB00nAWgIR0CdKhGe+VTrdX2UKGgGR0Bqiwz7/GVBaAdNTgFoCEdAnSwBKDkELnV9lChoBkfAMpyuuA7Pp2gHTRMBaAhHQJ0thuvUz9F1fZQoaAZHQGzedPk7wKBoB01rAWgIR0CdMKt3OfNBdX2UKGgGR0BuXibvw3HaaAdNPwFoCEdAnTJtdzGPxXV9lChoBkdAcFNxPwd8zGgHTUcBaAhHQJ00RilSCOF1fZQoaAZHQDMLCxeLNwBoB0vQaAhHQJ01orz5GjN1fZQoaAZHQHAyzvNNahZoB01VAWgIR0CdOapFCswMdX2UKGgGR0BtTTjin5zpaAdNbQFoCEdAnTxaKDTScHV9lChoBkdAbbgmY0EX+GgHTYUBaAhHQJ1BUpLEk0J1fZQoaAZHQEF2POpsGgVoB00gAWgIR0CdQ8zIV/MGdX2UKGgGR0BBPKpT/ACXaAdL42gIR0CdRb17IDHPdX2UKGgGR7/4DIV/MGHIaAdL4GgIR0CdR6dznzQNdX2UKGgGR0BuJgFFDv3KaAdNbQFoCEdAnUrVR+BpYnV9lChoBkdAathpwCKaX2gHTZQBaAhHQJ1NHnU2DQJ1fZQoaAZHQHBF02pAD7toB01qAWgIR0CdTz2alUIcdX2UKGgGR0BqW+rCFbmmaAdNXAFoCEdAnVJVndweeXV9lChoBkdAa/dZlnRLK2gHTT4BaAhHQJ1UOUt7KJV1fZQoaAZHQFE0NipeeFtoB01bAWgIR0CdVjHSF49pdX2UKGgGR0BrTO606YE4aAdNZwFoCEdAnVlX8TBZZHV9lChoBkdAcD0aQmu1W2gHTTcBaAhHQJ1bErYoRZl1fZQoaAZHwCalQoCuEEloB0vlaAhHQJ1ceTlkpZx1fZQoaAZHQEw2GfPHDJloB00eAWgIR0CdXhXfZVXFdX2UKGgGR0BwQAHnlnyvaAdNQgFoCEdAnWDz2alUInV9lChoBke/+vfdhy8zymgHTRsBaAhHQJ1igrVe8f51fZQoaAZHQFPAqASWZ7ZoB01eAWgIR0CdZH+7Dl5odX2UKGgGR0BvGvpyIYWMaAdNXQFoCEdAnWeR/d69kHV9lChoBkdAb+2KLsKLKmgHTWQBaAhHQJ1pkqNIbwV1fZQoaAZHQG1N6cAiml9oB011AWgIR0Cda7KdhAnldX2UKGgGR8AuqbG3nZCfaAdL+mgIR0CdbkfOlfqpdX2UKGgGR0BtjtK7I1cdaAdNagFoCEdAnXCJOerdWXV9lChoBkdAN2kwnH/952gHS95oCEdAnXIzG96C2HV9lChoBkdAbOVxiG34K2gHTUkBaAhHQJ12E/IKc/d1fZQoaAZHQELkc0cfeUJoB01DAWgIR0CdeJUdaMaTdX2UKGgGR0BwV3dHlOoHaAdNcwFoCEdAnXvD67/XG3V9lChoBkdAbGBV0cOsk2gHTVkBaAhHQJ2ASyB06o51fZQoaAZHQGtUptSAH3VoB01SAWgIR0CdgtSW7e2vdX2UKGgGR0BurtrXUYsNaAdNUwFoCEdAnYS6Ii1RcnV9lChoBkdAcOsj/dZaFGgHTaABaAhHQJ2IPg/C66J1fZQoaAZHQHI5FQAMlTpoB01uAWgIR0Cdila/yoXLdX2UKGgGRz/Rh4t6HCXQaAdNGwFoCEdAnYvwaNuLrHV9lChoBkdAQLYacZtNz2gHS+JoCEdAnY5ebExZdXV9lChoBkdAOvaCQLeANGgHTRwBaAhHQJ2P+lzltCR1fZQoaAZHQG0/5NXYDkloB01vAWgIR0Cdkf3Ytg8bdX2UKGgGR0ByBUBdUsFuaAdNgQFoCEdAnZUvub7TD3V9lChoBkdAb5uE0zj3mGgHTVABaAhHQJ2XH+717IF1fZQoaAZHQGwq6Ieo1k1oB01eAWgIR0CdmQwgDA8CdX2UKGgGR0Bug+WOZLIxaAdNbQFoCEdAnZwwDJU5uXV9lChoBkdAFoG6wt8NQWgHTQQBaAhHQJ2drZ/Tb351fZQoaAZHQG6pEovzvqloB01uAWgIR0Cdn8oa1kUcdX2UKGgGR0BwEN9ZzPrwaAdNXAFoCEdAnaLZkK/mDHV9lChoBkdAbK7kZJkGzWgHTVEBaAhHQJ2k03974SJ1fZQoaAZHwC/tmnO0LMNoB0vzaAhHQJ2mM6cRUWF1fZQoaAZHQEGYMsH0K7ZoB00PAWgIR0Cdp8ARTS9edX2UKGgGR0BvRmx0MgEEaAdNsgFoCEdAnavHKji4rnV9lChoBkdAcKhsGxD9fmgHTXwBaAhHQJ2uk96kZaV1fZQoaAZHQGzYBO58Sf1oB01VAWgIR0CdsSZ6lchUdX2UKGgGR0BxI9IbwSamaAdNeAFoCEdAnbXtZ3cHnnV9lChoBkdARoh9uxbB42gHTRIBaAhHQJ24XkyULUl1fZQoaAZHQEWS/dqL0jFoB01fAWgIR0Cdu2lJpWWAdWUu"}, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7fc2feee64d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc2feee6560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc2feee65f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc2feee6680>", "_build": "<function ActorCriticPolicy._build at 0x7fc2feee6710>", "forward": "<function ActorCriticPolicy.forward at 0x7fc2feee67a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc2feee6830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc2feee68c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc2feee6950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc2feee69e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc2feee6a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc2feee6b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc2feedc5c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1200128, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687972336902134015, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGaatTxBsaa8iEEvvifVRTw9Vxk+gGobvQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5860, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 48, "n_epochs": 5, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 sha256:78a87614a2e0539e44c8a95e2638cedcb7bebd0e042f2f8b9e8bbb84d181e756
-size 146081
+oid sha256:585fd18af6a6452746b9664a131ef661d44cac28538230d167816091ce3d1898
+size 146017

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 0x7f69e068bac0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f69e068bb50>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f69e068bbe0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f69e068bc70>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f69e068bd00>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f69e068bd90>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f69e068be20>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f69e068beb0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f69e068bf40>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f69e069c040>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f69e069c0d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f69e069c160>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc2feee64d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc2feee6560>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc2feee65f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc2feee6680>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc2feee6710>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc2feee67a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc2feee6830>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc2feee68c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc2feee6950>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc2feee69e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc2feee6a70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc2feee6b00>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f69e068df00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc2feedc5c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1000448,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 1200128,
+    "_total_timesteps": 1200000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1687962861203361809,
+    "start_time": 1687972336902134015,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZHDL4mIpw/HnWlvlsQnb7br1++omIGvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGaatTxBsaa8iEEvvifVRTw9Vxk+gGobvQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00044800000000000395,
+    "_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": 3908,
+    "_n_updates": 5860,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -83,8 +83,8 @@
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
+    "batch_size": 48,
+    "n_epochs": 5,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3996fec8e43d894cbc5a649edaf116defb9da36f723ea6d207f3871060ddc5c1
+oid sha256:0de55a497879e4fd3a8182b45bbe28e78dcdbb7489e41636f4090027134a8e4d
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2354c84e787260f0798b7a09e49f7446a20dbf7e376c57205d762c0ee301af9
+oid sha256:fd8450d8d7acb64e624970af63b17c4804d8e4c74e458e6c06672d48a4a6308d
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": 199.7897646, "std_reward": 97.20262878423938, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-28T15:10:54.770179"}
+{"mean_reward": 283.8390347, "std_reward": 18.164442769840264, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-28T17:54:17.533763"}