han-na commited on
Commit
e559f7e
1 Parent(s): 3116cce

upload a better model

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 218.00 +/- 86.87
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 289.18 +/- 15.57
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 0x7c756d3e5990>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c756d3e5a20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c756d3e5ab0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c756d3e5b40>", "_build": "<function ActorCriticPolicy._build at 0x7c756d3e5bd0>", "forward": "<function ActorCriticPolicy.forward at 0x7c756d3e5c60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c756d3e5cf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c756d3e5d80>", "_predict": "<function ActorCriticPolicy._predict at 0x7c756d3e5e10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c756d3e5ea0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c756d3e5f30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c756d3e5fc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c756d379440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1726580689326610555, "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": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "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 0x7a4703282f80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4703283010>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a47032830a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4703283130>", "_build": "<function ActorCriticPolicy._build at 0x7a47032831c0>", "forward": "<function ActorCriticPolicy.forward at 0x7a4703283250>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a47032832e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4703283370>", "_predict": "<function ActorCriticPolicy._predict at 0x7a4703283400>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4703283490>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4703283520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a47032835b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a470321e240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1726732717742680397, "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": -0.004885333333333408, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG64OF6AvteMAWyUS6OMAXSUR0Cqf1rmhdt3dX2UKGgGR0Bx59AzHjp+aAdNcwFoCEdAqn9mXHBDX3V9lChoBkdAc5oSoOx0MmgHS79oCEdAqn+imEXcg3V9lChoBkdAcaFjLSuyNWgHS8doCEdAqn/lG3F1jnV9lChoBkdAcwPQhOgxrWgHS7poCEdAqn/qTt9hJHV9lChoBkdAcvX+JP69CmgHS8JoCEdAqn/1kz41xnV9lChoBkdAb05y4FzMimgHS6poCEdAqoBVxbSql3V9lChoBkdAciRo3Jgb62gHS7RoCEdAqoBhAOavzXV9lChoBkdAcztQj2SMcmgHS7JoCEdAqoClAgPmP3V9lChoBkdActJxh2GIsWgHS71oCEdAqpB2u9vjwXV9lChoBkdAc2KtfXwsoWgHS81oCEdAqpCRFCswL3V9lChoBkdAcbM6HCXQdGgHS7VoCEdAqpChASnLq3V9lChoBkdAcWPxp+MIeGgHS7toCEdAqpCei5/b03V9lChoBkdAcu8AOrhismgHS89oCEdAqpC8pd8iOnV9lChoBkdAcrfQcPvrnmgHS69oCEdAqpDQcR15jnV9lChoBkdAcmy4aP0ZnGgHS7xoCEdAqpD8figkC3V9lChoBkdAc9KD1GsmwGgHS6loCEdAqpEQ1LrX2HV9lChoBkdAco5sWfseGWgHS7poCEdAqpGFhTfixXV9lChoBkdAcPzxtpEhJWgHS5JoCEdAqpGQWznienV9lChoBkdAcq2Jz1bqyGgHS7xoCEdAqpGdRk3CK3V9lChoBkdAch5beuV5bGgHS8VoCEdAqpGqi22G7HV9lChoBkdAczzp0wJw9GgHS/toCEdAqpGx6v7m+3V9lChoBkdAcfQcafjCHmgHS5FoCEdAqpIGjASFoXV9lChoBkdAcYT7gbZOBWgHS49oCEdAqpIOO6unuXV9lChoBkdAcrky0a6z3WgHS8RoCEdAqpIcpb2US3V9lChoBkdAcpH90zTF2mgHS75oCEdAqpJqgXdj5XV9lChoBkdAcxQDAaef7WgHS8hoCEdAqpJtytFKCnV9lChoBkdAchkrj5sTFmgHS69oCEdAqpKJ4lhPTHV9lChoBkdAQwYHgP3BYWgHS2FoCEdAqpKUF+uvEHV9lChoBkdAc3dtLteD4GgHS8poCEdAqpKxYNiH7HV9lChoBkdAclWBYV6/qWgHS8VoCEdAqpLUoYvWYnV9lChoBkdAc1y4mTkhimgHS7RoCEdAqpLYQvpQlHV9lChoBkdAdCWH9m6GxmgHS7poCEdAqpL7TBqKxnV9lChoBkdAcnuQ/5ckdGgHS75oCEdAqpOPS+g133V9lChoBkdAcac0nPVurWgHS7loCEdAqpOPIlt0m3V9lChoBkdAcyvBbOeJ52gHS81oCEdAqpOi9ytFKHV9lChoBkdAcaPQAdXDFmgHS5doCEdAqpOtGI9C/3V9lChoBkdAcnQFJQLuyGgHS8poCEdAqpPEDEFW4nV9lChoBkdAcidc1O0sv2gHS7poCEdAqpP4bbUPQXV9lChoBkdAcECJIUahpWgHS5hoCEdAqpQTySV4YHV9lChoBkdAc9jXZoPCmGgHS8doCEdAqpQTa7EpAnV9lChoBkdAcR1jghr302gHS7toCEdAqpRXbwjMV3V9lChoBkdAcL8btZ3cHmgHS75oCEdAqpRc9bHIZXV9lChoBkdAcdQXRw6ySmgHS7RoCEdAqpRrS3LFGXV9lChoBkdAcSyPLPldT2gHS5doCEdAqpSMAaNuL3V9lChoBkdAchVWY4Qz12gHS6doCEdAqpSSMir1d3V9lChoBkdAcy+kAxSHd2gHS9toCEdAqpT1Dtw71nV9lChoBkdAaJGeNkvsaGgHTegDaAhHQKqVFmGucMF1fZQoaAZHQHQGYhllK9RoB0vaaAhHQKqVGUeuFHt1fZQoaAZHQHFIIaYNRWNoB0uraAhHQKqVU3qAz551fZQoaAZHQHAfob4rSVpoB0unaAhHQKqVZJWeYlZ1fZQoaAZHQEfU7CiyprFoB0uGaAhHQKqVdha1Tit1fZQoaAZHQHOVkCRwIdFoB0u8aAhHQKqVkPBBRht1fZQoaAZHQHMcWzfJmuloB0vbaAhHQKqVzLt/nW91fZQoaAZHQHO+K4H5aeRoB0vTaAhHQKqV6kN4JNV1fZQoaAZHQHL2zw6QvHtoB0u3aAhHQKqV82w3YL91fZQoaAZHQHFAmCmMwURoB0uvaAhHQKqWHvcafjF1fZQoaAZHQHK++pjtoi9oB0vYaAhHQKqWKrJ8v251fZQoaAZHQHDhR51Ng0FoB0uuaAhHQKqWKoE0SAZ1fZQoaAZHQHDM3pOerdZoB0vJaAhHQKqWWUSqU/x1fZQoaAZHQHNKSiyprDZoB0u0aAhHQKqWXJjDsMR1fZQoaAZHQHIzRcqvvBtoB0vFaAhHQKqWfjNIK+l1fZQoaAZHQFMBjW07bL5oB0uTaAhHQKqWuNhE0BR1fZQoaAZHQHDeen2qT8poB0u7aAhHQKqWv7j1f3N1fZQoaAZHQHD32UGFBY5oB0uwaAhHQKqWwg2606Z1fZQoaAZHQHE+NvS+g15oB0u5aAhHQKqW2rkKeCl1fZQoaAZHQHCbcjqv/zdoB0unaAhHQKqXBnoPkJd1fZQoaAZHQHOO0eMhouhoB0u+aAhHQKqXKz9CNS91fZQoaAZHQHNnUlE7W/doB0vJaAhHQKqXbeTmnwZ1fZQoaAZHQHGBkX531SRoB0uyaAhHQKqXcEHMUyp1fZQoaAZHQHCG9a2WpqBoB0utaAhHQKqXgQgcLjR1fZQoaAZHQHI/1D8cdYJoB0ugaAhHQKqXlsyi22J1fZQoaAZHQEd6dtl7MPloB0teaAhHQKqXnJnQID51fZQoaAZHQHBRZ5u63ApoB0ueaAhHQKqXnIkJKJ51fZQoaAZHQHDh78Nx2jhoB0u2aAhHQKqXn93r2QJ1fZQoaAZHQHP+2kep4r1oB0vCaAhHQKqX62bXpW51fZQoaAZHQHG+h5kbxVhoB0u3aAhHQKqYA4Ds+mp1fZQoaAZHQHGFlOTJQtVoB0usaAhHQKqYDXiBGx51fZQoaAZHQHE9cY64lQdoB0vAaAhHQKqYFslb/wR1fZQoaAZHQHC/KFyq+8JoB0uWaAhHQKqYFjiGWUt1fZQoaAZHQG68eLNwBHVoB0umaAhHQKqYVb2USqV1fZQoaAZHQHEANgjQiRpoB0vAaAhHQKqYgiUPhAJ1fZQoaAZHQHIZa7/XGwRoB0u+aAhHQKqYx4SpR411fZQoaAZHQHPKKm0mdAhoB0u4aAhHQKqY4fYjB2x1fZQoaAZHQD6Y8La24NJoB0tYaAhHQKqY7Id2gWd1fZQoaAZHQHPVZpWV/tpoB0umaAhHQKqY++pwS8J1fZQoaAZHQHRezArQPZtoB0u5aAhHQKqZJjbSJCV1fZQoaAZHQHOcDKYAsCloB0u5aAhHQKqZOP91loV1fZQoaAZHQHMtM9Oh0yRoB0u0aAhHQKqZQskIHC51fZQoaAZHQHOLduxbB45oB0u8aAhHQKqZWGATZg51fZQoaAZHQHDppg1FYuFoB0vAaAhHQKqZZDuSfUZ1fZQoaAZHQHMlXLidat9oB0vIaAhHQKqZc3rD6311fZQoaAZHQHFI02pAD7toB0uVaAhHQKqZeH9m6Gx1fZQoaAZHQHG7/u1F6RhoB0u8aAhHQKqZpPhQ3xZ1fZQoaAZHQHJF0Oy3TeBoB0uyaAhHQKqZrYXfqHJ1fZQoaAZHQHEwaNp/PPdoB0u3aAhHQKqZr5a/yoZ1fZQoaAZHQHFmj4UN8VpoB0uraAhHQKqZ5iEQGwB1fZQoaAZHQHGlpQxesxRoB0uPaAhHQKqaIsK9f1J1fZQoaAZHQHHwi/KyOaRoB0u9aAhHQKqaNwx33Yd1fZQoaAZHQHLNJ0fYBeZoB0ubaAhHQKqaStKZlWh1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1232, "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": 0.995, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "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-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": "2.4.0+cu121", "GPU Enabled": "False", "Numpy": "1.26.4", "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 sha256:8c30406457bc00490495d90b1146868d6982e1bb19cbd2f23551a4cfea4ac953
3
- size 148088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4582b469a6365e0a374f86c5442123a5df3ef8de83aeadea065317f976703636
3
+ size 147446
ppo-LunarLander-v2/data CHANGED
@@ -4,34 +4,34 @@
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 0x7c756d3e5990>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c756d3e5a20>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c756d3e5ab0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c756d3e5b40>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7c756d3e5bd0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7c756d3e5c60>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c756d3e5cf0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c756d3e5d80>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7c756d3e5e10>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c756d3e5ea0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c756d3e5f30>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c756d3e5fc0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7c756d379440>"
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": 1726580689326610555,
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'>",
@@ -41,17 +41,17 @@
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
- "_current_progress_remaining": -0.015808000000000044,
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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",
@@ -78,13 +78,13 @@
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:": "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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 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 0x7a4703282f80>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4703283010>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a47032830a0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4703283130>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7a47032831c0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7a4703283250>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a47032832e0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4703283370>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7a4703283400>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4703283490>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4703283520>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a47032835b0>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7a470321e240>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 1507328,
25
+ "_total_timesteps": 1500000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1726732717742680397,
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'>",
 
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.004885333333333408,
45
  "_stats_window_size": 100,
46
  "ep_info_buffer": {
47
  ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "gAWV4gsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG64OF6AvteMAWyUS6OMAXSUR0Cqf1rmhdt3dX2UKGgGR0Bx59AzHjp+aAdNcwFoCEdAqn9mXHBDX3V9lChoBkdAc5oSoOx0MmgHS79oCEdAqn+imEXcg3V9lChoBkdAcaFjLSuyNWgHS8doCEdAqn/lG3F1jnV9lChoBkdAcwPQhOgxrWgHS7poCEdAqn/qTt9hJHV9lChoBkdAcvX+JP69CmgHS8JoCEdAqn/1kz41xnV9lChoBkdAb05y4FzMimgHS6poCEdAqoBVxbSql3V9lChoBkdAciRo3Jgb62gHS7RoCEdAqoBhAOavzXV9lChoBkdAcztQj2SMcmgHS7JoCEdAqoClAgPmP3V9lChoBkdActJxh2GIsWgHS71oCEdAqpB2u9vjwXV9lChoBkdAc2KtfXwsoWgHS81oCEdAqpCRFCswL3V9lChoBkdAcbM6HCXQdGgHS7VoCEdAqpChASnLq3V9lChoBkdAcWPxp+MIeGgHS7toCEdAqpCei5/b03V9lChoBkdAcu8AOrhismgHS89oCEdAqpC8pd8iOnV9lChoBkdAcrfQcPvrnmgHS69oCEdAqpDQcR15jnV9lChoBkdAcmy4aP0ZnGgHS7xoCEdAqpD8figkC3V9lChoBkdAc9KD1GsmwGgHS6loCEdAqpEQ1LrX2HV9lChoBkdAco5sWfseGWgHS7poCEdAqpGFhTfixXV9lChoBkdAcPzxtpEhJWgHS5JoCEdAqpGQWznienV9lChoBkdAcq2Jz1bqyGgHS7xoCEdAqpGdRk3CK3V9lChoBkdAch5beuV5bGgHS8VoCEdAqpGqi22G7HV9lChoBkdAczzp0wJw9GgHS/toCEdAqpGx6v7m+3V9lChoBkdAcfQcafjCHmgHS5FoCEdAqpIGjASFoXV9lChoBkdAcYT7gbZOBWgHS49oCEdAqpIOO6unuXV9lChoBkdAcrky0a6z3WgHS8RoCEdAqpIcpb2US3V9lChoBkdAcpH90zTF2mgHS75oCEdAqpJqgXdj5XV9lChoBkdAcxQDAaef7WgHS8hoCEdAqpJtytFKCnV9lChoBkdAchkrj5sTFmgHS69oCEdAqpKJ4lhPTHV9lChoBkdAQwYHgP3BYWgHS2FoCEdAqpKUF+uvEHV9lChoBkdAc3dtLteD4GgHS8poCEdAqpKxYNiH7HV9lChoBkdAclWBYV6/qWgHS8VoCEdAqpLUoYvWYnV9lChoBkdAc1y4mTkhimgHS7RoCEdAqpLYQvpQlHV9lChoBkdAdCWH9m6GxmgHS7poCEdAqpL7TBqKxnV9lChoBkdAcnuQ/5ckdGgHS75oCEdAqpOPS+g133V9lChoBkdAcac0nPVurWgHS7loCEdAqpOPIlt0m3V9lChoBkdAcyvBbOeJ52gHS81oCEdAqpOi9ytFKHV9lChoBkdAcaPQAdXDFmgHS5doCEdAqpOtGI9C/3V9lChoBkdAcnQFJQLuyGgHS8poCEdAqpPEDEFW4nV9lChoBkdAcidc1O0sv2gHS7poCEdAqpP4bbUPQXV9lChoBkdAcECJIUahpWgHS5hoCEdAqpQTySV4YHV9lChoBkdAc9jXZoPCmGgHS8doCEdAqpQTa7EpAnV9lChoBkdAcR1jghr302gHS7toCEdAqpRXbwjMV3V9lChoBkdAcL8btZ3cHmgHS75oCEdAqpRc9bHIZXV9lChoBkdAcdQXRw6ySmgHS7RoCEdAqpRrS3LFGXV9lChoBkdAcSyPLPldT2gHS5doCEdAqpSMAaNuL3V9lChoBkdAchVWY4Qz12gHS6doCEdAqpSSMir1d3V9lChoBkdAcy+kAxSHd2gHS9toCEdAqpT1Dtw71nV9lChoBkdAaJGeNkvsaGgHTegDaAhHQKqVFmGucMF1fZQoaAZHQHQGYhllK9RoB0vaaAhHQKqVGUeuFHt1fZQoaAZHQHFIIaYNRWNoB0uraAhHQKqVU3qAz551fZQoaAZHQHAfob4rSVpoB0unaAhHQKqVZJWeYlZ1fZQoaAZHQEfU7CiyprFoB0uGaAhHQKqVdha1Tit1fZQoaAZHQHOVkCRwIdFoB0u8aAhHQKqVkPBBRht1fZQoaAZHQHMcWzfJmuloB0vbaAhHQKqVzLt/nW91fZQoaAZHQHO+K4H5aeRoB0vTaAhHQKqV6kN4JNV1fZQoaAZHQHL2zw6QvHtoB0u3aAhHQKqV82w3YL91fZQoaAZHQHFAmCmMwURoB0uvaAhHQKqWHvcafjF1fZQoaAZHQHK++pjtoi9oB0vYaAhHQKqWKrJ8v251fZQoaAZHQHDhR51Ng0FoB0uuaAhHQKqWKoE0SAZ1fZQoaAZHQHDM3pOerdZoB0vJaAhHQKqWWUSqU/x1fZQoaAZHQHNKSiyprDZoB0u0aAhHQKqWXJjDsMR1fZQoaAZHQHIzRcqvvBtoB0vFaAhHQKqWfjNIK+l1fZQoaAZHQFMBjW07bL5oB0uTaAhHQKqWuNhE0BR1fZQoaAZHQHDeen2qT8poB0u7aAhHQKqWv7j1f3N1fZQoaAZHQHD32UGFBY5oB0uwaAhHQKqWwg2606Z1fZQoaAZHQHE+NvS+g15oB0u5aAhHQKqW2rkKeCl1fZQoaAZHQHCbcjqv/zdoB0unaAhHQKqXBnoPkJd1fZQoaAZHQHOO0eMhouhoB0u+aAhHQKqXKz9CNS91fZQoaAZHQHNnUlE7W/doB0vJaAhHQKqXbeTmnwZ1fZQoaAZHQHGBkX531SRoB0uyaAhHQKqXcEHMUyp1fZQoaAZHQHCG9a2WpqBoB0utaAhHQKqXgQgcLjR1fZQoaAZHQHI/1D8cdYJoB0ugaAhHQKqXlsyi22J1fZQoaAZHQEd6dtl7MPloB0teaAhHQKqXnJnQID51fZQoaAZHQHBRZ5u63ApoB0ueaAhHQKqXnIkJKJ51fZQoaAZHQHDh78Nx2jhoB0u2aAhHQKqXn93r2QJ1fZQoaAZHQHP+2kep4r1oB0vCaAhHQKqX62bXpW51fZQoaAZHQHG+h5kbxVhoB0u3aAhHQKqYA4Ds+mp1fZQoaAZHQHGFlOTJQtVoB0usaAhHQKqYDXiBGx51fZQoaAZHQHE9cY64lQdoB0vAaAhHQKqYFslb/wR1fZQoaAZHQHC/KFyq+8JoB0uWaAhHQKqYFjiGWUt1fZQoaAZHQG68eLNwBHVoB0umaAhHQKqYVb2USqV1fZQoaAZHQHEANgjQiRpoB0vAaAhHQKqYgiUPhAJ1fZQoaAZHQHIZa7/XGwRoB0u+aAhHQKqYx4SpR411fZQoaAZHQHPKKm0mdAhoB0u4aAhHQKqY4fYjB2x1fZQoaAZHQD6Y8La24NJoB0tYaAhHQKqY7Id2gWd1fZQoaAZHQHPVZpWV/tpoB0umaAhHQKqY++pwS8J1fZQoaAZHQHRezArQPZtoB0u5aAhHQKqZJjbSJCV1fZQoaAZHQHOcDKYAsCloB0u5aAhHQKqZOP91loV1fZQoaAZHQHMtM9Oh0yRoB0u0aAhHQKqZQskIHC51fZQoaAZHQHOLduxbB45oB0u8aAhHQKqZWGATZg51fZQoaAZHQHDppg1FYuFoB0vAaAhHQKqZZDuSfUZ1fZQoaAZHQHMlXLidat9oB0vIaAhHQKqZc3rD6311fZQoaAZHQHFI02pAD7toB0uVaAhHQKqZeH9m6Gx1fZQoaAZHQHG7/u1F6RhoB0u8aAhHQKqZpPhQ3xZ1fZQoaAZHQHJF0Oy3TeBoB0uyaAhHQKqZrYXfqHJ1fZQoaAZHQHEwaNp/PPdoB0u3aAhHQKqZr5a/yoZ1fZQoaAZHQHFmj4UN8VpoB0uraAhHQKqZ5iEQGwB1fZQoaAZHQHGlpQxesxRoB0uPaAhHQKqaIsK9f1J1fZQoaAZHQHHwi/KyOaRoB0u9aAhHQKqaNwx33Yd1fZQoaAZHQHLNJ0fYBeZoB0ubaAhHQKqaStKZlWh1ZS4="
49
  },
50
  "ep_success_buffer": {
51
  ":type:": "<class 'collections.deque'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
+ "_n_updates": 1232,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
 
78
  },
79
  "n_envs": 16,
80
  "n_steps": 1024,
81
+ "gamma": 0.995,
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": 8,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
90
  ":serialized:": "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"
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42865c1815ddce52586d8399dd273a0db3359960e8e9be7ec71283d3571e54f
3
- size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f6c819c961636848a978952e7774345ce4f0e03abcfb85efe45a9fcb4ce4c7
3
+ size 87978
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f45510d055925e300d830310cd0d3a1224ddfa83d108f3a43adf65270298f89
3
- size 43762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d1b6ceeccc5f98d98dab37dc69a04a7de0065cec6149f46ad4394782f91404
3
+ size 43634
ppo-LunarLander-v2/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0a5
4
  - PyTorch: 2.4.0+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0a5
4
  - PyTorch: 2.4.0+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.26.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 217.99771660000002, "std_reward": 86.87228888239144, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-17T14:45:29.359171"}
 
1
+ {"mean_reward": 289.17833479999996, "std_reward": 15.570794920779221, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-19T08:22:15.074888"}