Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +16 -16
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 255.97 +/- 18.27
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 0x7f24a201d6c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f24a201d750>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f24a201d7e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f24a201d870>", "_build": "<function ActorCriticPolicy._build at 0x7f24a201d900>", "forward": "<function ActorCriticPolicy.forward at 0x7f24a201d990>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f24a201da20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f24a201dab0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f24a201db40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f24a201dbd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f24a201dc60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f24a201dcf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2449d566c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684094777023066486, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 310, "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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7fd375b8ec20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd375b8ecb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd375b8ed40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd375b8edd0>", "_build": "<function ActorCriticPolicy._build at 0x7fd375b8ee60>", "forward": "<function ActorCriticPolicy.forward at 0x7fd375b8eef0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd375b8ef80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd375b8f010>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd375b8f0a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd375b8f130>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd375b8f1c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd375b8f250>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd3207f2ec0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684176944892770918, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV/gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHAIiFK02LqMAWyUS8uMAXSUR0CX1LkmQbMpdX2UKGgGR0BxK/0OEug6aAdLwGgIR0CYNphisny/dX2UKGgGR0BjA6S9ugpSaAdN6ANoCEdAmDc+xrzoU3V9lChoBkdAcgXLy+YdAGgHS9hoCEdAmDdnhKlHjXV9lChoBkdAcgVo9LYf4mgHS8VoCEdAmDjmSdOIqXV9lChoBkdAW0VxDLKV6mgHTegDaAhHQJg5uOFQEZB1fZQoaAZHQHF5kSZjQRhoB0vWaAhHQJg6HUz9CNV1fZQoaAZHQHHdLApKBd5oB00FAWgIR0CYOjaePJaJdX2UKGgGR0BxijxiG34LaAdNDgFoCEdAmDqqe9SMtXV9lChoBkdAcO09yLhrFmgHS8RoCEdAmDyLlq8DjnV9lChoBkdAcTLx3mmtQ2gHS8NoCEdAmD2NJ4B3inV9lChoBkdAcX7CTlkpZ2gHS+hoCEdAmD4iksSTQnV9lChoBkdAcLW274BV/GgHS8poCEdAmD47Nr0rb3V9lChoBkdAcUj0J4SpSGgHS8BoCEdAmD7zqrzXjHV9lChoBkdAce8vBacI7mgHTQYBaAhHQJg/ROYYzi11fZQoaAZHQHDjtfb9If9oB0viaAhHQJg/2B+Wnj11fZQoaAZHQHHv9kOI68xoB0u1aAhHQJhAOySmqHZ1fZQoaAZHQHAkBFmWdEtoB0vWaAhHQJhAf+dbxEx1fZQoaAZHQG/l/8l5WzZoB0vNaAhHQJhAtnrY5DJ1fZQoaAZHQHJsPwAlv61oB01HAWgIR0CYQSI4VARkdX2UKGgGR0Bwza4pc5bRaAdNBgFoCEdAmELM/t6X0HV9lChoBkdAcM3RaHKwIWgHTQkBaAhHQJhDQYVIqb11fZQoaAZHQG98XbdrO7hoB0veaAhHQJhDTazu4PR1fZQoaAZHQHCVYXGff41oB0vOaAhHQJhDvyBkI5Z1fZQoaAZHQHBWHIdU83doB0vKaAhHQJhENgUlAu91fZQoaAZHQG7ecCo0hvBoB0vOaAhHQJhFOzQeFL51fZQoaAZHQHA15wsGxD9oB0vHaAhHQJhFXojfNzN1fZQoaAZHQHARfVRUFStoB0v0aAhHQJhFqRISUTt1fZQoaAZHQHD26aLGaQVoB0u0aAhHQJhF2SU1Q691fZQoaAZHQHBgOHnEETxoB0vJaAhHQJhGv0rbxmV1fZQoaAZHQHB/t1U2kzpoB0vNaAhHQJhHF3LV4HJ1fZQoaAZHQHGF63VkMCtoB0vxaAhHQJhI1ubZvk11fZQoaAZHQG6gPWQOnVJoB0vEaAhHQJhJqVQhwER1fZQoaAZHQHGskAT7EYRoB0vtaAhHQJhLQ4BFNL11fZQoaAZHQHKwg5aNdZ9oB00FAWgIR0CYS5wKjSG8dX2UKGgGR0BQ4azmfXf7aAdL0WgIR0CYTJRa5f+kdX2UKGgGR0BxO/IOpbUxaAdL9mgIR0CYTL6p5u63dX2UKGgGR0Bvfaz/p+tsaAdLymgIR0CYTQ2fkFOgdX2UKGgGR0Bxl52U0Nz9aAdL5WgIR0CYTYSuQp4KdX2UKGgGR0BieyTQmeDnaAdN6ANoCEdAmE7NfG+9J3V9lChoBkdAbzzTIeYD1WgHS+RoCEdAmE8sEmplz3V9lChoBkdAbv9AgPmPo2gHS7BoCEdAmE+HzH0btXV9lChoBkdAYzygKWszVWgHTegDaAhHQJhQb9/BnBd1fZQoaAZHQHAbgwfyPMloB02OAWgIR0CYUdxbjcVQdX2UKGgGR0Bvo/BBRhttaAdLrGgIR0CYUghTOxB3dX2UKGgGR0BwrtFDv3JxaAdNRgFoCEdAmFMbw4KhMHV9lChoBkdAcOFjRlYlp2gHS8JoCEdAmFYcFMZgonV9lChoBkdAcb3reIl+mWgHS7JoCEdAmFZHiFTNuHV9lChoBkdAcfhLhrFfiWgHTS4BaAhHQJhWxRbbDdh1fZQoaAZHQHMHmkN4JNVoB00MAWgIR0CYVtHs1KoRdX2UKGgGR0Bwb2f29L6DaAdNGwFoCEdAmFfh4QjD9HV9lChoBkdAb94r6tT1kGgHS8VoCEdAmFgG2PT5PHV9lChoBkdAcePZi/fwZ2gHTQkBaAhHQJhZTjjrAxl1fZQoaAZHQHCpkhq0tyxoB0vJaAhHQJhZ2dJ8OTd1fZQoaAZHQHGPH8baRIVoB0u4aAhHQJhaZ4Uvf0p1fZQoaAZHQGE2VQQ+UyJoB03oA2gIR0CYWwev6j33dX2UKGgGR0BxlhnVXmvGaAdNIAFoCEdAmFzx1gYxcnV9lChoBkdAbup3Tuv2XmgHS7VoCEdAmF00Q04zanV9lChoBkdAcekj7hvR7mgHS8BoCEdAmF10qUeMh3V9lChoBkdAcoGNfw7T2GgHS9VoCEdAmF7Bt+CsfnV9lChoBkdAbzqCsfaHsWgHS7toCEdAmF7Q4jrzG3V9lChoBkdAcSnv1DjR2WgHS+xoCEdAmF+QLqlgt3V9lChoBkdAb0k54nndPGgHS79oCEdAmGA8tPHktHV9lChoBkdAcH9/zasZHmgHS/NoCEdAmGDZYs/Y8XV9lChoBkdAcLAt3wCr92gHS+xoCEdAmGNw/gR9PXV9lChoBkdAZHRKmsNlRWgHTegDaAhHQJhjjlQuVX51fZQoaAZHQG6nGKZUkv9oB0u9aAhHQJhjnpD/lyR1fZQoaAZHQHH38WXTmXBoB00XAWgIR0CYY+H9WIXTdX2UKGgGR0BwWuya/h2oaAdL0mgIR0CYZLocaOxTdX2UKGgGR0BwHGNDMNc4aAdLzWgIR0CYZjuyu6mPdX2UKGgGR0BxvLeyiVSoaAdNRgFoCEdAmGpSY9gWrXV9lChoBkdAcm09Htnf22gHS/toCEdAmGr3w9aEBnV9lChoBkdAcZkXpGFzuGgHS65oCEdAmGuko4MnZ3V9lChoBkdAXMrwBo24u2gHTegDaAhHQJhsjnNgSe11fZQoaAZHQHGEmkBS1mdoB0vRaAhHQJhuGRnvlU91fZQoaAZHQHICJ1zQu29oB0vxaAhHQJhvQydnTRZ1fZQoaAZHQG++b+T/yXloB0vUaAhHQJhvtXDFZPl1fZQoaAZHQGBhrRBu4w1oB03oA2gIR0CYcuck+otMdX2UKGgGR0BxU3/tIClraAdNEgFoCEdAmHThpUPxx3V9lChoBkdAcRX5NoJzDGgHS85oCEdAmHVgj2SMcnV9lChoBkdAcdoAG0NSZWgHS+FoCEdAmHcTa9K28nV9lChoBkdAZDL7XxvvSmgHTegDaAhHQJh3WJrLyMF1fZQoaAZHQG8QL5ZbILhoB0vOaAhHQJh3pMCcPOJ1fZQoaAZHQGVB078vVVhoB03oA2gIR0CYeGEfkmx/dX2UKGgGR0Bt1LT+ee4DaAdLvWgIR0CYeGFqzqrzdX2UKGgGR0BxtkBNmDlHaAdLr2gIR0CYeSvXbuc+dX2UKGgGR0BvHwO4G2TgaAdLwGgIR0CYeZX9zfaYdX2UKGgGR0BzNdgMMI/raAdNEQFoCEdAmHnvGEPDpHV9lChoBkdAcFEIxQBPsWgHS9toCEdAmH58IeHSGHV9lChoBkdAcRl3+uNgjWgHS8FoCEdAmH7iBK+SKXV9lChoBkdAcbTxMFlkH2gHS7poCEdAmH9pMpPRA3V9lChoBkdAcOcOskpqh2gHS9hoCEdAmH+Y7FKkEnV9lChoBkdAccjZzxPO6mgHS6ZoCEdAmH+ZJK8L8nV9lChoBkdAcPfCwbEP2GgHS8RoCEdAmH/FXiiqQ3V9lChoBkdAcna2dd3Sr2gHTQoBaAhHQJh/9E0BOpN1fZQoaAZHQHDX3rUsnRdoB0vbaAhHQJiAE/u9eyB1fZQoaAZHQHD8T2Jzkp9oB0vhaAhHQJiBSx5cC5p1fZQoaAZHQHE16uW8h9toB0v7aAhHQJiC8Ia99MN1fZQoaAZHQGH7hz/6wdNoB03oA2gIR0CYhMwIdELIdX2UKGgGR0BxbwnrpqyoaAdLq2gIR0CYhRQYUFjedWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2c989a2853fddce7341791321b0732d6a8679c89f072ae89ca3dc2aa09b034f
|
3 |
+
size 146662
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,12 +26,12 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,7 +45,7 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fd375b8ec20>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd375b8ecb0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd375b8ed40>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd375b8edd0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd375b8ee60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd375b8eef0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd375b8ef80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd375b8f010>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd375b8f0a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd375b8f130>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd375b8f1c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd375b8f250>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fd3207f2ec0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1684176944892770918,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c68b057ddadf902a50e94e6f3f8ad673d7b750757acc282314564a9d9dcf09c
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9f824def0dd48862f8a7c21d3bc6700941f407ae46af097146e3245fc208754
|
3 |
size 43329
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 255.97454417871214, "std_reward": 18.27109391951685, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-15T19:36:29.714991"}
|