| { | |
| "policy_class": { | |
| ":type:": "<class 'abc.ABCMeta'>", | |
| ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", | |
| "__module__": "stable_baselines3.common.policies", | |
| "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x0000022D4ABAAB80>", | |
| "__abstractmethods__": "frozenset()", | |
| "_abc_impl": "<_abc._abc_data object at 0x0000022D4ABA8E00>" | |
| }, | |
| "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.dict.Dict'>", | |
| ":serialized:": "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", | |
| "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", | |
| "_shape": null, | |
| "dtype": null, | |
| "_np_random": null | |
| }, | |
| "action_space": { | |
| ":type:": "<class 'gym.spaces.box.Box'>", | |
| ":serialized:": "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", | |
| "dtype": "float32", | |
| "_shape": [ | |
| 7 | |
| ], | |
| "low": "[-1. -1. -1. -1. -1. -1. -1.]", | |
| "high": "[1. 1. 1. 1. 1. 1. 1.]", | |
| "bounded_below": "[ True True True True True True True]", | |
| "bounded_above": "[ True True True True True True True]", | |
| "_np_random": null | |
| }, | |
| "n_envs": 1, | |
| "num_timesteps": 0, | |
| "_total_timesteps": 0, | |
| "_num_timesteps_at_start": 0, | |
| "seed": null, | |
| "action_noise": null, | |
| "start_time": null, | |
| "learning_rate": 0.0007, | |
| "tensorboard_log": "runs/zna5ecxa", | |
| "lr_schedule": { | |
| ":type:": "<class 'function'>", | |
| ":serialized:": "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" | |
| }, | |
| "_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, | |
| "ep_info_buffer": null, | |
| "ep_success_buffer": null, | |
| "_n_updates": 0, | |
| "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 | |
| } |