| { | |
| "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 0x7f75cb94cb80>", | |
| "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f75cb94cc10>", | |
| "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f75cb94cca0>", | |
| "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f75cb94cd30>", | |
| "_build": "<function ActorCriticPolicy._build at 0x7f75cb94cdc0>", | |
| "forward": "<function ActorCriticPolicy.forward at 0x7f75cb94ce50>", | |
| "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f75cb94cee0>", | |
| "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f75cb94cf70>", | |
| "_predict": "<function ActorCriticPolicy._predict at 0x7f75cb94d000>", | |
| "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f75cb94d090>", | |
| "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f75cb94d120>", | |
| "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f75cb94d1b0>", | |
| "__abstractmethods__": "frozenset()", | |
| "_abc_impl": "<_abc._abc_data object at 0x7f75cbe5cb80>" | |
| }, | |
| "verbose": 1, | |
| "policy_kwargs": {}, | |
| "num_timesteps": 0, | |
| "_total_timesteps": 0, | |
| "_num_timesteps_at_start": 0, | |
| "seed": null, | |
| "action_noise": null, | |
| "start_time": 0.0, | |
| "learning_rate": 0.0003, | |
| "tensorboard_log": null, | |
| "_last_obs": null, | |
| "_last_episode_starts": null, | |
| "_last_original_obs": null, | |
| "_episode_num": 0, | |
| "use_sde": false, | |
| "sde_sample_freq": -1, | |
| "_current_progress_remaining": 1.0, | |
| "_stats_window_size": 100, | |
| "ep_info_buffer": null, | |
| "ep_success_buffer": null, | |
| "_n_updates": 0, | |
| "observation_space": { | |
| ":type:": "<class 'gymnasium.spaces.box.Box'>", | |
| ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", | |
| "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": 1, | |
| "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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" | |
| } | |
| } |