| { | |
| "policy_class": { | |
| ":type:": "<class 'typing.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 0x0000017A6121EEF0>", | |
| "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000017A6121EF80>", | |
| "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000017A6121F010>", | |
| "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000017A6121F0A0>", | |
| "_build": "<function ActorCriticPolicy._build at 0x0000017A6121F130>", | |
| "forward": "<function ActorCriticPolicy.forward at 0x0000017A6121F1C0>", | |
| "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000017A6121F250>", | |
| "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000017A6121F2E0>", | |
| "_predict": "<function ActorCriticPolicy._predict at 0x0000017A6121F370>", | |
| "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000017A6121F400>", | |
| "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000017A6121F490>", | |
| "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000017A6121F520>", | |
| "__abstractmethods__": "frozenset()", | |
| "_abc_impl": "<_abc._abc_data object at 0x0000017A60005300>" | |
| }, | |
| "verbose": 1, | |
| "policy_kwargs": { | |
| ":type:": "<class 'dict'>", | |
| ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", | |
| "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", | |
| "optimizer_kwargs": { | |
| "alpha": 0.99, | |
| "eps": 1e-05, | |
| "weight_decay": 0 | |
| } | |
| }, | |
| "observation_space": { | |
| ":type:": "<class 'gym.spaces.box.Box'>", | |
| ":serialized:": "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", | |
| "dtype": "float32", | |
| "_shape": [ | |
| 4 | |
| ], | |
| "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", | |
| "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", | |
| "bounded_below": "[ True True True True]", | |
| "bounded_above": "[ True True True True]", | |
| "_np_random": null | |
| }, | |
| "action_space": { | |
| ":type:": "<class 'gym.spaces.discrete.Discrete'>", | |
| ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", | |
| "n": 2, | |
| "_shape": [], | |
| "dtype": "int64", | |
| "_np_random": null | |
| }, | |
| "n_envs": 1, | |
| "num_timesteps": 1000, | |
| "_total_timesteps": 1000, | |
| "_num_timesteps_at_start": 0, | |
| "seed": null, | |
| "action_noise": null, | |
| "start_time": 1676220973590136300, | |
| "learning_rate": 0.0007, | |
| "tensorboard_log": null, | |
| "lr_schedule": { | |
| ":type:": "<class 'function'>", | |
| ":serialized:": "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" | |
| }, | |
| "_last_obs": { | |
| ":type:": "<class 'numpy.ndarray'>", | |
| ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAHXrhT6JYT4/lj2MO4YGE7+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu" | |
| }, | |
| "_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": 0.0, | |
| "ep_info_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "ep_success_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "_n_updates": 20000, | |
| "n_steps": 5, | |
| "gamma": 0.99, | |
| "gae_lambda": 1.0, | |
| "ent_coef": 0.0, | |
| "vf_coef": 0.5, | |
| "max_grad_norm": 0.5, | |
| "normalize_advantage": false | |
| } |