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 +27 -27
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/pytorch_variables.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +5 -5
- 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: 248.89 +/- 18.93
|
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 0x7fd3f4238550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f42385e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f4238670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f4238700>", "_build": "<function ActorCriticPolicy._build at 0x7fd3f4238790>", "forward": "<function ActorCriticPolicy.forward at 0x7fd3f4238820>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f42388b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f4238940>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f42389d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f4238a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f4238af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f4238b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd3f422a7c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2031616, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685435985051718772, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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:": "gAWV8QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHM8L+xW1dCMAWyUS/eMAXSUR0ChH36bvw3HdX2UKGgGR0ByrB7v5P/JaAdL8mgIR0ChH41eKKpDdX2UKGgGR0BwDNf8dgfEaAdL4WgIR0ChH8bDMvAXdX2UKGgGR0Bw7W8SPEKmaAdL+WgIR0ChIChtLteEdX2UKGgGR0BxBT84xUNsaAdL5GgIR0ChIJsSK3uvdX2UKGgGR0ByBA08/2TQaAdNLAFoCEdAoSELTH80lHV9lChoBkdAc9s8m8dxQ2gHS+JoCEdAoSEzQu27WnV9lChoBkdAc1GwTufEoGgHS+doCEdAoSFH+XJHRXV9lChoBkdAcb2tFKCg9WgHS+RoCEdAoSFNWXC0nnV9lChoBkdAb0E+K0lZ5mgHS9ZoCEdAoSFyLuQZGnV9lChoBkdAcIlQFs54nmgHS9doCEdAoSHY3zcynHV9lChoBkdAcL0QU5+6RWgHS+xoCEdAoSHYjQiRn3V9lChoBkdAcei+u/1xsGgHS/FoCEdAoSJCUmlZYHV9lChoBkdAcGor0aqCH2gHS+poCEdAoSJrCBPKuHV9lChoBkdAcgIgsbvPT2gHS+JoCEdAoSJ9m+TNdXV9lChoBkdAbmyofjjrA2gHS/poCEdAoSLOvKU3XXV9lChoBkdAcQ65HEuQIWgHS+5oCEdAoSLYqTbFj3V9lChoBkdAcVIfqHGjsWgHS99oCEdAoSLwow22onV9lChoBkdAb9qVE/jbSWgHS99oCEdAoSOF/QSi/XV9lChoBkdAcheSgGr0a2gHTRkBaAhHQKEjhKqXF991fZQoaAZHQG+XXx4IKMNoB0vIaAhHQKEk7qM3qA11fZQoaAZHQG/RMaCL/CJoB00EAWgIR0ChJO7xd6cBdX2UKGgGR0ByyVz/6wdKaAdL1mgIR0ChJPVrAP/adX2UKGgGR0Byf0uQIUrTaAdL8mgIR0ChJTL+o99udX2UKGgGR0ByO3t2LYPHaAdL8GgIR0ChJVv557gLdX2UKGgGR0Bwf0xO+IuXaAdL/2gIR0ChJcfxMFlkdX2UKGgGR0BNg+IMz/IbaAdLpmgIR0ChJhafzz3AdX2UKGgGR0Bx8RNlAeJYaAdL7mgIR0ChJkUhmoR7dX2UKGgGR0ByZ+DdxhlUaAdL2GgIR0ChJrpzcRDkdX2UKGgGR0By3XtiQT24aAdNDAFoCEdAoSba5AhStXV9lChoBkdAcaCu3trsSmgHS+hoCEdAoSdYwCbMHXV9lChoBkdAcrS5DJEH+2gHS+JoCEdAoSdeoLofS3V9lChoBkdAcpG/lhgE2mgHS/9oCEdAoSdxTsIE83V9lChoBkdAc1pwPAfuC2gHS/VoCEdAoShiuKXOW3V9lChoBkdAcsZ+fAbhnGgHS/poCEdAoSiCRr8BMnV9lChoBkdAbsLu4wyqMmgHS95oCEdAoSmEyi22HHV9lChoBkdAcpxYR/ViF2gHS81oCEdAoSmdO45LiHV9lChoBkdActEO801qFmgHS+9oCEdAoSnrJCBwuXV9lChoBkdAcfegq3EycmgHS/VoCEdAoSpbOs1baHV9lChoBkdAcMIrCWNWEWgHTRIBaAhHQKEqxtiQT251fZQoaAZHQHCMMnRb8m9oB0vraAhHQKEq2uq3mV91fZQoaAZHQG+j/yf+S8toB0vwaAhHQKErU9jgAIZ1fZQoaAZHQHFWwFgUlAxoB0v3aAhHQKErvOIInjR1fZQoaAZHQHJ1Q+EAYHhoB0v1aAhHQKEsPIGyHEd1fZQoaAZHQHKsTxLCemNoB0vUaAhHQKEsTkRzzVd1fZQoaAZHQHL8livxH5JoB0vkaAhHQKEsi+7Dl5p1fZQoaAZHQHLxNEofCANoB00PAWgIR0ChLPBun/DMdX2UKGgGR0Bx1b3qRlpXaAdNBAFoCEdAoS0pIxxku3V9lChoBkdAb1163y7PIGgHS+poCEdAoS2PfEXLvHV9lChoBkdAc1BvW6K+BmgHS/loCEdAoS2v/YJ3PnV9lChoBkdAcK/3ai9Iw2gHS8xoCEdAoS3QBtDUmXV9lChoBkdAczUlVLi++WgHTQQBaAhHQKEukhib2Dh1fZQoaAZHQHDT76Hj6vdoB0vpaAhHQKEuvHmzSkV1fZQoaAZHQG+1JhWo3rFoB00LAWgIR0ChLvrhaTwEdX2UKGgGR0BxhNHy3CsPaAdL62gIR0ChLwm8/UvxdX2UKGgGR0BwyPKQq7ROaAdL8WgIR0ChLy3Z5AyEdX2UKGgGR0BxMkkfLcKxaAdL3GgIR0ChLyxyOq//dX2UKGgGR0BzCvDBMzuXaAdL1GgIR0ChL5sc6vJSdX2UKGgGR0ByQraqS5iFaAdNCAFoCEdAoTAChi9ZinV9lChoBkdAcnUJbdJrcmgHS/NoCEdAoTAECNjslnV9lChoBkdAchJre67NCGgHS+loCEdAoTARDCxeLXV9lChoBkdAbg/NliBoVWgHS99oCEdAoTBiE384xXV9lChoBkdAc06fjS5RTGgHS91oCEdAoTDGNzbN8nV9lChoBkdAcnfIy0rsjWgHS91oCEdAoTDpUJfICHV9lChoBkdAbPZ1zySV4WgHTSoBaAhHQKExS1cdHUd1fZQoaAZHQHFHQemvW6NoB0vLaAhHQKExjPIGQjl1fZQoaAZHQHEaX18LKFJoB00JAWgIR0ChMbMKLKmsdX2UKGgGR0BtMuQ8wHqvaAdL1mgIR0ChMg4lyBCldX2UKGgGR0BxLpeLNwBHaAdL72gIR0ChMqkTxoZidX2UKGgGR0BGdeh4+r2haAdLsGgIR0ChMq+RgZ0kdX2UKGgGR0BzsbLNfPX1aAdL/mgIR0ChMuI6Kcd6dX2UKGgGR0ByEVScbzbwaAdL4WgIR0ChMvKF7D2rdX2UKGgGR0BwDeh7E5yVaAdNGgFoCEdAoTMwz3yqdnV9lChoBkdAcyjZLIxQBWgHTS4BaAhHQKEzM4c3l0Z1fZQoaAZHQHEAIr4Fia1oB0vlaAhHQKEzciRGMGZ1fZQoaAZHQG8GPcrRSgpoB0vcaAhHQKEzsGs3hn91fZQoaAZHQHBcTn7pFCtoB0v7aAhHQKEzvk078vV1fZQoaAZHQGZ/Reb/ffpoB03oA2gIR0ChNCehPCVKdX2UKGgGR0BxdPW07bL2aAdL6GgIR0ChNDSj59E1dX2UKGgGR0BwyRtXPqs2aAdL/WgIR0ChNJc5CF9KdX2UKGgGR0ByM4FlkH2RaAdL7GgIR0ChNLQqqfe2dX2UKGgGR0BxDZpCa7VbaAdL4GgIR0ChNUo6r/83dX2UKGgGR0BvPO89Oh0yaAdL+mgIR0ChNVBp5/smdX2UKGgGR0BxeaZc9nscaAdNDAFoCEdAoTVsgIQe3nV9lChoBkdAcEHMxoIv8WgHS85oCEdAoTWWX7cfvHV9lChoBkdAcBa9US7GvWgHS9poCEdAoTW6Tr3TNXV9lChoBkdAcSMjhky1u2gHS99oCEdAoTYGB6KLsXV9lChoBkdAchzfhddE9mgHS/FoCEdAoTY00vXbunV9lChoBkdAcwyWRigCfmgHS+xoCEdAoTZnT9bX6XV9lChoBkdAVRNt/FzdUWgHS7loCEdAoTaww7DEWXV9lChoBkdAcTtrO7g882gHTQMBaAhHQKE2sy1uzhR1fZQoaAZHQHJfzfaYeDFoB0v0aAhHQKE2uVi4J/p1fZQoaAZHQHCOUHQhOgxoB0vsaAhHQKE25tNSIgx1fZQoaAZHQHP91wxWT5hoB0vxaAhHQKE26cp9ZzR1fZQoaAZHQHDYOsDGLk1oB0vyaAhHQKE3XblijL11fZQoaAZHQHLwmDL8rI5oB0vZaAhHQKE3lMt9QXR1fZQoaAZHQG/yhl18stloB0vjaAhHQKE3mlenhsJ1fZQoaAZHQHKQTvd/J/5oB0vKaAhHQKE34N5t3wF1fZQoaAZHQHI0QblzU7VoB0vbaAhHQKE4Gpda+vh1fZQoaAZHQHCcotcv/R5oB0vaaAhHQKE4f7x/d691ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "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": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "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": "2.0.1+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 0x7d2a7f632cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2a7f632d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2a7f632dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2a7f632e60>", "_build": "<function ActorCriticPolicy._build at 0x7d2a7f632ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7d2a7f632f80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2a7f633010>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2a7f6330a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d2a7f633130>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2a7f6331c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2a7f633250>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2a7f6332e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d2a7f6262c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1729571729814284782, "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": 248, "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": 16, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 sha256:6ff4af683bec2f6c294278d2c543cf580ce502b6efb429f6085b6c3001e8dbb6
|
3 |
+
size 148012
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,38 +4,38 @@
|
|
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": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
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'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
@@ -45,16 +45,16 @@
|
|
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'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
-
":serialized:": "
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
@@ -77,23 +77,23 @@
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
-
"n_steps":
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "
|
98 |
}
|
99 |
}
|
|
|
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 0x7d2a7f632cb0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2a7f632d40>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2a7f632dd0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2a7f632e60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7d2a7f632ef0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7d2a7f632f80>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2a7f633010>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2a7f6330a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7d2a7f633130>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2a7f6331c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2a7f633250>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2a7f6332e0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d2a7f6262c0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1729571729814284782,
|
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'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
|
|
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'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 248,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
+
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
}
|
99 |
}
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272d33288df33aab168fd78971c64db9d177b4a1d846694d92ad4febe080a8cb
|
3 |
+
size 88362
|
ppo-LunarLander-v2/policy.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 sha256:9ba5973986df4488db8e1c3445d6a2a7e22d42543f16e358cc84a0c4e297baf6
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.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 sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-
|
2 |
-
- Python: 3.10.
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
-
- Cloudpickle:
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
+
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.4.1+cu121
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 3.1.0
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 248.88721412339783, "std_reward": 18.92633994012914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-22T04:57:14.285193"}
|