Upload PPO LunarLander-v3 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v3.zip +2 -2
- ppo-LunarLander-v3/data +24 -24
- ppo-LunarLander-v3/policy.optimizer.pth +2 -2
- ppo-LunarLander-v3/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 286.52 +/- 19.23
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f0f87f769d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0f87f76a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0f87f76af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0f87f76b80>", "_build": "<function ActorCriticPolicy._build at 0x7f0f87f76c10>", "forward": "<function ActorCriticPolicy.forward at 0x7f0f87f76ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0f87f76d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0f87f76dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0f87f76e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0f87f76ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0f87f76f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f0f87f6fc90>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651696660.5679111, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 128, "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, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.10 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0a0+bfe5ad2", "GPU Enabled": "True", "Numpy": "1.22.0", "Gym": "0.21.0"}}
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f2f2036ad30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2f2036adc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2f2036ae50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2f2036aee0>", "_build": "<function ActorCriticPolicy._build at 0x7f2f2036af70>", "forward": "<function ActorCriticPolicy.forward at 0x7f2f202ed040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2f202ed0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2f202ed160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2f202ed1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2f202ed280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2f202ed310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2f20364780>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 6946816, "_total_timesteps": 6946816, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651738671.9991987, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIQRGLGPa7c0CUhpRSlIwBbJRLm4wBdJRHQLGl+TL4etF1fZQoaAZoCWgPQwhPIOwUq4hvQJSGlFKUaBVLh2gWR0Cxpf/tIClrdX2UKGgGaAloD0MI+u3rwPkQc0CUhpRSlGgVS6RoFkdAsaYBGus90XV9lChoBmgJaA9DCCLfpdSldHFAlIaUUpRoFUuhaBZHQLGmBoicG1R1fZQoaAZoCWgPQwhq3Qa1H61zQJSGlFKUaBVLyWgWR0Cxpg1ZcLSedX2UKGgGaAloD0MIoDL+fQZLckCUhpRSlGgVS71oFkdAsaYWVpsXSHV9lChoBmgJaA9DCGB4JclzH3NAlIaUUpRoFUuZaBZHQLGmF1FpfyB1fZQoaAZoCWgPQwiGVbyRuUpyQJSGlFKUaBVLpWgWR0Cxphstf5UMdX2UKGgGaAloD0MIaAQb1z9NcECUhpRSlGgVS5RoFkdAsaYb5aePJnV9lChoBmgJaA9DCJo/prUp1nFAlIaUUpRoFUuXaBZHQLGmH6PbO/t1fZQoaAZoCWgPQwhsI57sJipyQJSGlFKUaBVLjWgWR0CxpjZJsfq5dX2UKGgGaAloD0MICJChY0clckCUhpRSlGgVS4RoFkdAsaY4qBmPHXV9lChoBmgJaA9DCCtu3GL+hHJAlIaUUpRoFUuLaBZHQLGmQaEzwc51fZQoaAZoCWgPQwg58kBkkRVyQJSGlFKUaBVLomgWR0Cxpkj4HoovdX2UKGgGaAloD0MIs5lDUsvicUCUhpRSlGgVS5NoFkdAsaZOuwHJLnV9lChoBmgJaA9DCJUtknYjiXBAlIaUUpRoFUujaBZHQLGmUExZdOZ1fZQoaAZoCWgPQwhXz0nvG4NzQJSGlFKUaBVLqmgWR0CxplNITXardX2UKGgGaAloD0MIwlCHFe60cECUhpRSlGgVS5hoFkdAsaZaOq//N3V9lChoBmgJaA9DCLdj6q4sFnJAlIaUUpRoFUuoaBZHQLGmYq+Jxed1fZQoaAZoCWgPQwjd71AUqLhxQJSGlFKUaBVLp2gWR0CxpmmFev6kdX2UKGgGaAloD0MIy/Pg7uy7cECUhpRSlGgVS4hoFkdAsaZpJoTPB3V9lChoBmgJaA9DCP+vOnKkHHBAlIaUUpRoFUuQaBZHQLGmbQEpy6t1fZQoaAZoCWgPQwhUxVT6SZxzQJSGlFKUaBVLqWgWR0CxpnJ6IFeOdX2UKGgGaAloD0MIu18F+G4scUCUhpRSlGgVS6JoFkdAsaZ9YB/7SHV9lChoBmgJaA9DCDkM5q8Q63JAlIaUUpRoFUuiaBZHQLGmfjXnQpp1fZQoaAZoCWgPQwg26iEancZxQJSGlFKUaBVLpWgWR0CxpoRqCYkWdX2UKGgGaAloD0MIUfUrnY+5ckCUhpRSlGgVS41oFkdAsaaOCf6Gg3V9lChoBmgJaA9DCN0kBoHVjHNAlIaUUpRoFUufaBZHQLGmm+jM3ZR1fZQoaAZoCWgPQwgst7QaktNwQJSGlFKUaBVLl2gWR0CxpqAJ9iMHdX2UKGgGaAloD0MI+DjThK0ecUCUhpRSlGgVS5NoFkdAsaalE9dNWXV9lChoBmgJaA9DCP94r1rZ53JAlIaUUpRoFUuPaBZHQLGmrK2rn1Z1fZQoaAZoCWgPQwiQgqeQa5RzQJSGlFKUaBVLn2gWR0CxprKKDTScdX2UKGgGaAloD0MIAyfbwB0Dc0CUhpRSlGgVS6BoFkdAsaa0v/R3NnV9lChoBmgJaA9DCOdSXFU2n3BAlIaUUpRoFUuaaBZHQLGmuz/ZM+N1fZQoaAZoCWgPQwiDh2nfXKJxQJSGlFKUaBVLo2gWR0CxptDQJHAidX2UKGgGaAloD0MIaccNv9sKcUCUhpRSlGgVS5ZoFkdAsabR6Skj5nV9lChoBmgJaA9DCB/ZXDUP+nFAlIaUUpRoFUunaBZHQLGm0x+8Xep1fZQoaAZoCWgPQwiI2jaMgmRzQJSGlFKUaBVLtmgWR0CxptZul41QdX2UKGgGaAloD0MIHm6HhsVkb0CUhpRSlGgVS5JoFkdAsabawwCbMHV9lChoBmgJaA9DCHIVi99UY3FAlIaUUpRoFUuFaBZHQLGm42BreqJ1fZQoaAZoCWgPQwi8lSU6S9xzQJSGlFKUaBVLwmgWR0Cxpufze40/dX2UKGgGaAloD0MIHTo978YLc0CUhpRSlGgVS7loFkdAsabztb9qDnV9lChoBmgJaA9DCKipZWv9D3BAlIaUUpRoFUuUaBZHQLGm+mTTvy91fZQoaAZoCWgPQwgcBvNXiMNzQJSGlFKUaBVLuWgWR0CxpvpFLFn7dX2UKGgGaAloD0MIIa0x6ITjcECUhpRSlGgVS5toFkdAsacCWmgrY3V9lChoBmgJaA9DCExPWOJBWXFAlIaUUpRoFUuBaBZHQLGnA8hs67x1fZQoaAZoCWgPQwiHTWTmQlpyQJSGlFKUaBVLmGgWR0CxpwVhoduHdX2UKGgGaAloD0MIgAwdO2ijcECUhpRSlGgVS5loFkdAsacTlzU7S3V9lChoBmgJaA9DCFHex9EcwXBAlIaUUpRoFUueaBZHQLGnHP/7zkJ1fZQoaAZoCWgPQwjlfRzNEWNxQJSGlFKUaBVLfGgWR0CxpyIX40uUdX2UKGgGaAloD0MIhnZOs0CNcECUhpRSlGgVS4RoFkdAsaciBDohZHV9lChoBmgJaA9DCMprJXQX8HFAlIaUUpRoFUu/aBZHQLGnI5/9YOl1fZQoaAZoCWgPQwi/0Y4b/tBxQJSGlFKUaBVLf2gWR0CxpyhdD6WPdX2UKGgGaAloD0MI6BN5kjSkcECUhpRSlGgVS5RoFkdAsacsezUqhHV9lChoBmgJaA9DCNZSQNr/v3NAlIaUUpRoFUuiaBZHQLGnNdHDrJN1fZQoaAZoCWgPQwh0z7pGi5JyQJSGlFKUaBVLn2gWR0Cxp0RlDneSdX2UKGgGaAloD0MI2PULdoPccUCUhpRSlGgVS6loFkdAsadPp0OmSHV9lChoBmgJaA9DCMzTuaKUCnNAlIaUUpRoFUuWaBZHQLGnVuQp4KR1fZQoaAZoCWgPQwi8ehUZ3T1yQJSGlFKUaBVLjWgWR0Cxp1sbWEsbdX2UKGgGaAloD0MIxAlMpzXncECUhpRSlGgVS6BoFkdAsaddOqNp/XV9lChoBmgJaA9DCEZ+/RBbsnFAlIaUUpRoFUusaBZHQLGnXoaUA1h1fZQoaAZoCWgPQwioixTKgqtyQJSGlFKUaBVLn2gWR0Cxp2fXXiBHdX2UKGgGaAloD0MIPzVeuolgcUCUhpRSlGgVS6VoFkdAsadotGus93V9lChoBmgJaA9DCJ+sGK5ObXFAlIaUUpRoFUuQaBZHQLGnbcN6PbR1fZQoaAZoCWgPQwjKFd7l4otxQJSGlFKUaBVLh2gWR0Cxp3FxXGOudX2UKGgGaAloD0MI3h6EgLz1ckCUhpRSlGgVS5BoFkdAsad7Sro4dnV9lChoBmgJaA9DCGYzh6QWy3BAlIaUUpRoFUuIaBZHQLGngL74zrN1fZQoaAZoCWgPQwjt153uPBBxQJSGlFKUaBVLoGgWR0Cxp4Tin5zpdX2UKGgGaAloD0MItoR80PPCcECUhpRSlGgVS55oFkdAsaeFLQHAynV9lChoBmgJaA9DCAq8k0+PmXNAlIaUUpRoFUuhaBZHQLGnm1zhgmZ1fZQoaAZoCWgPQwjQ04BBUn9zQJSGlFKUaBVLv2gWR0Cxp6ApF1B/dX2UKGgGaAloD0MIHR7C+OlzcUCUhpRSlGgVS4JoFkdAsaeoflp48nV9lChoBmgJaA9DCKrU7IGWWXNAlIaUUpRoFUumaBZHQLGnrfaHsTp1fZQoaAZoCWgPQwgct5ifW8pzQJSGlFKUaBVLrGgWR0Cxp7yiAUcodX2UKGgGaAloD0MIH7k16XYJcECUhpRSlGgVS4toFkdAsafAj3VTaXV9lChoBmgJaA9DCFGf5A7bPHJAlIaUUpRoFUufaBZHQLGnwso2GZh1fZQoaAZoCWgPQwi63ct9MvBxQJSGlFKUaBVLp2gWR0Cxp8a77Kq5dX2UKGgGaAloD0MIFCLgEOpOcECUhpRSlGgVS5poFkdAsafJaaCtinV9lChoBmgJaA9DCP2C3bCtznJAlIaUUpRoFUuuaBZHQLGnyTiKiwl1fZQoaAZoCWgPQwgxfhr35iJzQJSGlFKUaBVLpWgWR0Cxp9YRZlnRdX2UKGgGaAloD0MIzxQ6rzEjckCUhpRSlGgVS6VoFkdAsafaLl3hXXV9lChoBmgJaA9DCEshkEtcI3FAlIaUUpRoFUuZaBZHQLGn3U1AJLN1fZQoaAZoCWgPQwihhQSMbsxxQJSGlFKUaBVLlmgWR0Cxp+Tt9hJAdX2UKGgGaAloD0MIpdqn4zGmcUCUhpRSlGgVS6xoFkdAsafuRzRx+HV9lChoBmgJaA9DCAdcV8xIl3NAlIaUUpRoFUu1aBZHQLGn+HLA57x1fZQoaAZoCWgPQwj0iTxJehhxQJSGlFKUaBVLlWgWR0Cxp/7Q1JlKdX2UKGgGaAloD0MIrb8lAL9Kc0CUhpRSlGgVS6hoFkdAsagGw7kn1HV9lChoBmgJaA9DCN82UyFeSXJAlIaUUpRoFUucaBZHQLGoC+fywwF1fZQoaAZoCWgPQwhubHak+vo5QJSGlFKUaBVLXmgWR0CxqBoC6pYLdX2UKGgGaAloD0MIzLOSVjxhckCUhpRSlGgVS6hoFkdAsagZkAggYHV9lChoBmgJaA9DCGQFvw2xA3JAlIaUUpRoFUubaBZHQLGoH9t/Fzd1fZQoaAZoCWgPQwhXz0nvm35vQJSGlFKUaBVLj2gWR0CxqCG+9Jz1dX2UKGgGaAloD0MIMjhKXp24cECUhpRSlGgVS5hoFkdAsaghggHNYHV9lChoBmgJaA9DCJQyqaHN3HNAlIaUUpRoFUuhaBZHQLGoKIoVmBh1fZQoaAZoCWgPQwhJvhJIiY1yQJSGlFKUaBVLfGgWR0CxqCj/MnqndX2UKGgGaAloD0MIWMnH7oJNc0CUhpRSlGgVS6toFkdAsagzv0AcUHV9lChoBmgJaA9DCJ612y70c3RAlIaUUpRoFUu2aBZHQLGoOnp0OmR1fZQoaAZoCWgPQwiwPEhPkbdyQJSGlFKUaBVLqGgWR0CxqD5ssQNDdX2UKGgGaAloD0MIYW9iSE62ckCUhpRSlGgVS49oFkdAsag+SwGGEnV9lChoBmgJaA9DCGMK1jgbmG9AlIaUUpRoFUuEaBZHQLGoQIY3vQZ1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2120, "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, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.10 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0a0+bfe5ad2", "GPU Enabled": "True", "Numpy": "1.22.0", "Gym": "0.21.0"}}
|
ppo-LunarLander-v3.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 sha256:6f701fef3dafdcb019f970ab76ada395beb04e87bed8585feff7e2cfdb45c077
|
3 |
+
size 143990
|
ppo-LunarLander-v3/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -42,12 +42,12 @@
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -66,24 +66,24 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining":
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
-
"n_steps":
|
80 |
-
"gamma": 0.
|
81 |
-
"gae_lambda": 0.
|
82 |
-
"ent_coef": 0.
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f2f2036ad30>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2f2036adc0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2f2036ae50>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2f2036aee0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f2f2036af70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f2f202ed040>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2f202ed0d0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f2f202ed160>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2f202ed1f0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2f202ed280>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2f202ed310>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2f20364780>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 6946816,
|
46 |
+
"_total_timesteps": 6946816,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1651738671.9991987,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": 0.0,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 2120,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
+
"n_epochs": 10,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
ppo-LunarLander-v3/policy.optimizer.pth
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:ab86aadc9a8ed51e4ebb133ce7c812a536665c869c9cb78f30acb652a52d4ad1
|
3 |
+
size 84893
|
ppo-LunarLander-v3/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fda84ef80ba5e11157b9864df3e0bd6a813f3c85e7f333fbb3ecffef98a82cf
|
3 |
size 43201
|
replay.mp4
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 sha256:14ba54bda3727cf519febeb96fe0b17135c768f615cac6c014216fbea72b11a5
|
3 |
+
size 199733
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 286.5166884018884, "std_reward": 19.22544595567936, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T09:46:28.872728"}
|