Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 271.22 +/- 22.45
+      value: 244.93 +/- 82.42
       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 0x7a4b5a2709d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4b5a270a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a4b5a270af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4b5a270b80>", "_build": "<function ActorCriticPolicy._build at 0x7a4b5a270c10>", "forward": "<function ActorCriticPolicy.forward at 0x7a4b5a270ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a4b5a270d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4b5a270dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7a4b5a270e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4b5a270ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4b5a270f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a4b5a271000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a4b5a268900>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2000896, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711355546897561542, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM2rZz1IF4W6KI/jOSdNgbVgCNu5l9gDuQAAgD8AAIA/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": -0.00044800000000000395, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGzgmrCFbmmMAWyUS+2MAXSUR0CjlsMH0K7adX2UKGgGR0BvxDENvwVkaAdNCAFoCEdAo5fOkJrtV3V9lChoBkdAcld47Rv3rWgHTS0BaAhHQKOYVCAtnPF1fZQoaAZHQHJvoku6ErZoB00UAWgIR0CjmMr74zrNdX2UKGgGR0BysabpeNT+aAdNKQFoCEdAo5lTQRf4RHV9lChoBkdANr/dIoVmBmgHS6xoCEdAo5oo5o4+83V9lChoBkdAcyazHjp9qmgHTQkBaAhHQKOam0ygwoN1fZQoaAZHQGK3Q0O3DvVoB03oA2gIR0CjnOgKF7D3dX2UKGgGR0ByIQl5WzWxaAdNIAFoCEdAo51s+u/1x3V9lChoBkdAcDarDZUT+WgHTQsBaAhHQKOd431BdD91fZQoaAZHQHIQsDOkcjtoB00iAWgIR0CjnvGgBcRldX2UKGgGR0Bwr/Mnqmj1aAdNCQFoCEdAo59szdk8R3V9lChoBkdAcR5tKqXF+GgHTRQBaAhHQKOf7V3EAHV1fZQoaAZHQHDd0ka/ATJoB00PAWgIR0CjoGki+tbLdX2UKGgGR0BwwZMYdhiLaAdL6GgIR0CjoWnG8274dX2UKGgGR0Bvlb0SRKYiaAdL92gIR0CjoeOb7TDwdX2UKGgGR0BxI0N3GGVSaAdNCwFoCEdAo6JYlfJFLHV9lChoBkdAcKJsyi22HGgHS/loCEdAo6LD37DVIHV9lChoBkdAcGkjD8+A3GgHTR8BaAhHQKOj1Q3xWkt1fZQoaAZHQHKDLjYI0IloB00ZAWgIR0CjpFSflIVedX2UKGgGR0BvS/Wz4UN8aAdNEQFoCEdAo6TKVfNRnHV9lChoBkdAcJYpFkQPJGgHTRUBaAhHQKOl0XnhbW51fZQoaAZHQHJ8r1uivgZoB01EAWgIR0CjpmF9BrvcdX2UKGgGR0Byh5iWmgrZaAdNAwFoCEdAo6bSSJTESHV9lChoBkdAcqoSAYpDu2gHTTQBaAhHQKOnWGHpKSR1fZQoaAZHQHC8GZ7XxvxoB00OAWgIR0CjqKf0ulGgdX2UKGgGR0BvpiEBbOeKaAdNSwFoCEdAo6lviDM/yHV9lChoBkdAb0Xg/C66KGgHTQIBaAhHQKOqHYRNATt1fZQoaAZHQHJpQ9mpVCJoB00+AWgIR0Cjq/LF4s3AdX2UKGgGR0BtDlklNUOvaAdL8mgIR0CjrIRqwhW6dX2UKGgGR0BwQWsT37DVaAdNKwFoCEdAo60IlSjxkXV9lChoBkdAcdDG8Empl2gHTR8BaAhHQKOthW7voeR1fZQoaAZHQHDE+hsZYPpoB000AWgIR0CjrpfzBhx6dX2UKGgGR0BweAEB8x9HaAdNHwFoCEdAo68UXvYvnXV9lChoBkdAcfsWSU1Q7GgHTQUBaAhHQKOvivugHu91fZQoaAZHQHFg0m2LHdZoB01JAWgIR0CjsKfA9FF2dX2UKGgGR0Aphga3qiXZaAdLvGgIR0CjsPin5zo2dX2UKGgGR0BvfcVpKzzFaAdNSAFoCEdAo7GH1anrIHV9lChoBkdAcbZYxtYSx2gHTQYBaAhHQKOyAEwnH/91fZQoaAZHQEOl/SYw7DFoB0vBaAhHQKOyWi+tbLV1fZQoaAZHQG1WpjDsMRZoB0vwaAhHQKOzVTx5LRN1fZQoaAZHQHAH5mEoOQRoB0vxaAhHQKOzw6FuejF1fZQoaAZHQHB/om1IAfdoB00QAWgIR0CjtEJ4B3iadX2UKGgGR0BOsZ5qubI+aAdLsmgIR0CjtJEdeY2LdX2UKGgGR0Bxqx+QU5+6aAdNqAFoCEdAo7XdbTtsvnV9lChoBkdAVTCiM5wOv2gHS7VoCEdAo7Y1E1EVnHV9lChoBkdARZxpBX0Xg2gHS5ZoCEdAo7Z3n0TURXV9lChoBkdAbbB5mAbyY2gHTRkBaAhHQKO27/rjYI11fZQoaAZHQDZEYR/ViF1oB0u+aAhHQKO30uxrzoV1fZQoaAZHQG+q5TZQHiZoB00yAWgIR0CjuGTQ/oq1dX2UKGgGR0BICIzN2TxHaAdLsGgIR0CjuLFxGUfQdX2UKGgGR0BxBeB3A2ycaAdL+2gIR0CjuSMYdhiLdX2UKGgGR0BxIO9IwudxaAdNJgFoCEdAo7o8lqrR0HV9lChoBkdAcH+z6rNnoWgHTQgBaAhHQKO6tEx7AtZ1fZQoaAZHQG1iF6Z6UqxoB0v+aAhHQKO7JD6WPcV1fZQoaAZHQHD8qQmu1WtoB0v8aAhHQKO7mEf1Yhd1fZQoaAZHQG5tPmYBvJloB00TAWgIR0CjvJl49ovjdX2UKGgGR0BuUKr/82rGaAdL52gIR0CjvP6ScLBsdX2UKGgGR0BwOX4/NZ/1aAdL6mgIR0CjvWXX7LuAdX2UKGgGR0BxfIu7HyVfaAdNGAFoCEdAo73f+4smOXV9lChoBkdAbrSdTYNAkmgHS+VoCEdAo77SZhKDkHV9lChoBkdASx/aURnOB2gHS7BoCEdAo78dxZMcqHV9lChoBkdAcYgM+eOGTWgHTWoBaAhHQKO/xCUHIIZ1fZQoaAZHQHESJZjhDPZoB00WAWgIR0CjwEE+xGDudX2UKGgGR0BwJZY7q6e5aAdNFAFoCEdAo8GtHDrJKnV9lChoBkdAZQ3ZnL7oCGgHTegDaAhHQKPE+K0D2al1fZQoaAZHQHKTr3PAwf1oB00IAWgIR0CjxX9S/CZXdX2UKGgGR0BwrxiRW912aAdNYAFoCEdAo8Yd7tzCDXV9lChoBkdAcHsm8/UvwmgHS+RoCEdAo8aCJTER8XV9lChoBkdAb7U+/xlQM2gHTQkBaAhHQKPHgilBQep1fZQoaAZHQG9u4JNTLntoB0v8aAhHQKPH9Eb5uZV1fZQoaAZHQHLrUK/mDDloB00JAmgIR0CjyOSqU/wBdX2UKGgGR0BzA7AymALBaAdNVAFoCEdAo8oNI/Z/TnV9lChoBkdAS2UXizcAR2gHS8NoCEdAo8pmZ1FH8XV9lChoBkdAcoWKR+z+m2gHTXkBaAhHQKPLD3fQ8fV1fZQoaAZHQHBzhZU1hstoB00ZAmgIR0CjzI/NzKcNdX2UKGgGR0BP0C9RJmNBaAdLr2gIR0CjzN3Zf2K3dX2UKGgGR0ByLf/zasZHaAdNagJoCEdAo86ZEBsAN3V9lChoBkdAcrSScbzbvmgHTXgBaAhHQKPPR3+MqBp1fZQoaAZHQHAildHDrJNoB0v3aAhHQKPPud6sySF1fZQoaAZHQHGLqsySFGpoB00GAWgIR0Cj0Dn9m6GydX2UKGgGR0Bvv7K7qY7aaAdNCgFoCEdAo9FPMSsbN3V9lChoBkdAb87KQJXyRWgHTU0BaAhHQKPR5zI3irF1fZQoaAZHQG8FOFHrhR9oB00EAWgIR0Cj0lsDW9UTdX2UKGgGR0BwsBb/wRXfaAdNIwFoCEdAo9NfIfbKzXV9lChoBkdAcuSNYbKif2gHTQsBaAhHQKPT2woLG711fZQoaAZHQFNBwdsBQvZoB0uraAhHQKPUJUMoc711fZQoaAZHQFFYRDkU9IRoB0vBaAhHQKPUeFL39Jl1fZQoaAZHQHEk02gnMMZoB01XAWgIR0Cj1ZRG2CumdX2UKGgGR0BwzuBnSOR1aAdNiAFoCEdAo9ZFT3qRl3V9lChoBkdAR2O/WUbDM2gHS7NoCEdAo9aS7sfJWHV9lChoBkdAcqQ++dsi0WgHTSABaAhHQKPXD3SKFZh1fZQoaAZHQEOq5I6Kcd5oB0uxaAhHQKPX5F4s3AF1fZQoaAZHQHJCT0Yj0MBoB0v6aAhHQKPYVdld1Md1fZQoaAZHQHEOYXKr7wdoB01PAWgIR0Cj2OkAggX/dX2UKGgGR0Bky0UZeiSJaAdN6ANoCEdAo9wbVrhzeXV9lChoBkdAcU9NtIkJKWgHS/VoCEdAo9y3FR51NnV9lChoBkdAZB5jYqXnhmgHTegDaAhHQKPfb65XlsB1fZQoaAZHQHGYMPjGT9toB00cAWgIR0Cj4JM90RvndX2UKGgGR0BGiPd2xIJ7aAdL4GgIR0Cj4PUo0ALidWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7816, "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": 0.01, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "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 0x7daf6b2ce050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7daf6b2ce0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7daf6b2ce170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7daf6b2ce200>", "_build": "<function ActorCriticPolicy._build at 0x7daf6b2ce290>", "forward": "<function ActorCriticPolicy.forward at 0x7daf6b2ce320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7daf6b2ce3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7daf6b2ce440>", "_predict": "<function ActorCriticPolicy._predict at 0x7daf6b2ce4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7daf6b2ce560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7daf6b2ce5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7daf6b2ce680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7daf6b2d8cc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3000320, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711410760814288384, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAlsTwcLjy8+UimvMrpgj3jVvy5doG1uQAAgD8AAIA/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:": "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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": 2048, "gamma": 0.99, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 sha256:39dc2879b413511295ed31a4c08fb6f49f7b722263d8b4789ddb345dff2fad70
-size 146871
+oid sha256:cb571cb9f4977e309b82d32f88ddbff4ad20b950ed4fd0eabf4f0aa981e1ff38
+size 147305

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 0x7a4b5a2709d0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4b5a270a60>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a4b5a270af0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4b5a270b80>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a4b5a270c10>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a4b5a270ca0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a4b5a270d30>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4b5a270dc0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a4b5a270e50>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4b5a270ee0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4b5a270f70>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a4b5a271000>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7daf6b2ce050>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7daf6b2ce0e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7daf6b2ce170>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7daf6b2ce200>",
+        "_build": "<function ActorCriticPolicy._build at 0x7daf6b2ce290>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7daf6b2ce320>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7daf6b2ce3b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7daf6b2ce440>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7daf6b2ce4d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7daf6b2ce560>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7daf6b2ce5f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7daf6b2ce680>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a4b5a268900>"
+        "_abc_impl": "<_abc._abc_data object at 0x7daf6b2d8cc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 2000896,
-    "_total_timesteps": 2000000,
+    "num_timesteps": 3000320,
+    "_total_timesteps": 3000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1711355546897561542,
+    "start_time": 1711410760814288384,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM2rZz1IF4W6KI/jOSdNgbVgCNu5l9gDuQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAlsTwcLjy8+UimvMrpgj3jVvy5doG1uQAAgD8AAIA/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": 7816,
+    "_n_updates": 5860,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -77,8 +77,8 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 1024,
-    "gamma": 0.999,
+    "n_steps": 2048,
+    "gamma": 0.99,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f599ae22fdba0a146af71e34ab0b70f37c68206211b65298a9a56033b45d2acb
-size 87978
+oid sha256:8c332ede0dfe2954285e73c82442d980eef9d7a177fc0537d19b32d3e2f4c544
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4257c3996cc57dcd77020daf33bc933480c1cdf4e2bb76e237de23e312086a5c
-size 43634
+oid sha256:ec97ba48664b21ac340ec9c36777f45edc70dc45a81b1e7a1e5f8fa95d1b957c
+size 43762

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.2.1+cu121
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1

results.json

@@ -1 +1 @@
-{"mean_reward": 271.22164807203814, "std_reward": 22.4471081184336, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-25T09:35:34.830025"}
+{"mean_reward": 244.92605136480242, "std_reward": 82.42489859433904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T01:24:42.320732"}