|
{ |
|
"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 0x7aecb6a65900>", |
|
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7aecb6a65990>", |
|
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7aecb6a65a20>", |
|
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7aecb6a65ab0>", |
|
"_build": "<function ActorCriticPolicy._build at 0x7aecb6a65b40>", |
|
"forward": "<function ActorCriticPolicy.forward at 0x7aecb6a65bd0>", |
|
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7aecb6a65c60>", |
|
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7aecb6a65cf0>", |
|
"_predict": "<function ActorCriticPolicy._predict at 0x7aecb6a65d80>", |
|
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7aecb6a65e10>", |
|
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7aecb6a65ea0>", |
|
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7aecb6a65f30>", |
|
"__abstractmethods__": "frozenset()", |
|
"_abc_impl": "<_abc._abc_data object at 0x7aecb7271180>" |
|
}, |
|
"verbose": 1, |
|
"policy_kwargs": { |
|
":type:": "<class 'dict'>", |
|
":serialized:": "gAWVjgAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA1hY3RpdmF0aW9uX2ZulIwbdG9yY2gubm4ubW9kdWxlcy5hY3RpdmF0aW9ulIwEUmVMVZSTlIwIbmV0X2FyY2iUXZR9lCiMAnBplF2UKE0AAU0AAWWMAnZmlF2UKE0AAU0AAWV1YXUu", |
|
"log_std_init": -2, |
|
"ortho_init": false, |
|
"activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", |
|
"net_arch": [ |
|
{ |
|
"pi": [ |
|
256, |
|
256 |
|
], |
|
"vf": [ |
|
256, |
|
256 |
|
] |
|
} |
|
] |
|
}, |
|
"num_timesteps": 100352, |
|
"_total_timesteps": 100000, |
|
"_num_timesteps_at_start": 0, |
|
"seed": null, |
|
"action_noise": null, |
|
"start_time": 1711892386789825170, |
|
"learning_rate": 2.0633e-05, |
|
"tensorboard_log": null, |
|
"_last_obs": { |
|
":type:": "<class 'numpy.ndarray'>", |
|
":serialized:": "gAWV/QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaIAAAAAAAAAKcgFbhjGqI/gnFFWNLQs78k9/EYet6ev2oxX7PJtcw/WBQn20YYcz8bggrSzF/NP4xuJL0wZMA/KTBz2I91qL+jHXkkNk4DQPVDlXZ3Zui/KYtp44zr67/h9BsNib4mQM57gYwCggpAW5WMnbmXGUDFSRRU2vYoQH+JG13ZYB7ASOlVJ66J4L+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLEYaUjAFDlHSUUpQu" |
|
}, |
|
"_last_episode_starts": { |
|
":type:": "<class 'numpy.ndarray'>", |
|
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg==" |
|
}, |
|
"_last_original_obs": null, |
|
"_episode_num": 0, |
|
"use_sde": false, |
|
"sde_sample_freq": -1, |
|
"_current_progress_remaining": -0.0035199999999999676, |
|
"_stats_window_size": 100, |
|
"ep_info_buffer": { |
|
":type:": "<class 'collections.deque'>", |
|
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" |
|
}, |
|
"ep_success_buffer": { |
|
":type:": "<class 'collections.deque'>", |
|
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" |
|
}, |
|
"_n_updates": 4320, |
|
"observation_space": { |
|
":type:": "<class 'gymnasium.spaces.box.Box'>", |
|
":serialized:": "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", |
|
"dtype": "float64", |
|
"bounded_below": "[False False False False False False False False False False False False\n False False False False False]", |
|
"bounded_above": "[False False False False False False False False False False False False\n False False False False False]", |
|
"_shape": [ |
|
17 |
|
], |
|
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf]", |
|
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]", |
|
"low_repr": "-inf", |
|
"high_repr": "inf", |
|
"_np_random": null |
|
}, |
|
"action_space": { |
|
":type:": "<class 'gymnasium.spaces.box.Box'>", |
|
":serialized:": "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", |
|
"dtype": "float32", |
|
"bounded_below": "[ True True True True True True]", |
|
"bounded_above": "[ True True True True True True]", |
|
"_shape": [ |
|
6 |
|
], |
|
"low": "[-1. -1. -1. -1. -1. -1.]", |
|
"high": "[1. 1. 1. 1. 1. 1.]", |
|
"low_repr": "-1.0", |
|
"high_repr": "1.0", |
|
"_np_random": null |
|
}, |
|
"n_envs": 1, |
|
"n_steps": 512, |
|
"gamma": 0.98, |
|
"gae_lambda": 0.92, |
|
"ent_coef": 0.000401762, |
|
"vf_coef": 0.58096, |
|
"max_grad_norm": 0.8, |
|
"batch_size": 64, |
|
"n_epochs": 20, |
|
"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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" |
|
} |
|
} |