| { | |
| "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 0x7fae2436dca0>", | |
| "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fae2436dd30>", | |
| "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fae2436ddc0>", | |
| "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fae2436de50>", | |
| "_build": "<function ActorCriticPolicy._build at 0x7fae2436dee0>", | |
| "forward": "<function ActorCriticPolicy.forward at 0x7fae2436df70>", | |
| "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fae24371040>", | |
| "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fae243710d0>", | |
| "_predict": "<function ActorCriticPolicy._predict at 0x7fae24371160>", | |
| "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fae243711f0>", | |
| "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fae24371280>", | |
| "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fae24371310>", | |
| "__abstractmethods__": "frozenset()", | |
| "_abc_impl": "<_abc._abc_data object at 0x7fae24370600>" | |
| }, | |
| "verbose": 1, | |
| "policy_kwargs": { | |
| ":type:": "<class 'dict'>", | |
| ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", | |
| "log_std_init": -2, | |
| "ortho_init": false, | |
| "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", | |
| "optimizer_kwargs": { | |
| "alpha": 0.99, | |
| "eps": 1e-05, | |
| "weight_decay": 0 | |
| } | |
| }, | |
| "num_timesteps": 32, | |
| "_total_timesteps": 20, | |
| "_num_timesteps_at_start": 0, | |
| "seed": null, | |
| "action_noise": null, | |
| "start_time": 1682158815516267321, | |
| "learning_rate": 0.00096, | |
| "tensorboard_log": null, | |
| "lr_schedule": { | |
| ":type:": "<class 'function'>", | |
| ":serialized:": "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" | |
| }, | |
| "_last_obs": { | |
| ":type:": "<class 'numpy.ndarray'>", | |
| ":serialized:": "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" | |
| }, | |
| "_last_episode_starts": { | |
| ":type:": "<class 'numpy.ndarray'>", | |
| ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg==" | |
| }, | |
| "_last_original_obs": { | |
| ":type:": "<class 'numpy.ndarray'>", | |
| ":serialized:": "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" | |
| }, | |
| "_episode_num": 0, | |
| "use_sde": true, | |
| "sde_sample_freq": -1, | |
| "_current_progress_remaining": -0.6000000000000001, | |
| "_stats_window_size": 100, | |
| "ep_info_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "ep_success_buffer": { | |
| ":type:": "<class 'collections.deque'>", | |
| ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" | |
| }, | |
| "_n_updates": 1, | |
| "n_steps": 8, | |
| "gamma": 0.99, | |
| "gae_lambda": 0.9, | |
| "ent_coef": 0.0, | |
| "vf_coef": 0.4, | |
| "max_grad_norm": 0.5, | |
| "normalize_advantage": false, | |
| "observation_space": { | |
| ":type:": "<class 'gym.spaces.box.Box'>", | |
| ":serialized:": "gAWVZwIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLHIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWcAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lGgKSxyFlIwBQ5R0lFKUjARoaWdolGgSKJZwAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH+UaApLHIWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLHIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaCFLHIWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=", | |
| "dtype": "float32", | |
| "_shape": [ | |
| 28 | |
| ], | |
| "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", | |
| "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", | |
| "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", | |
| "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", | |
| "_np_random": null | |
| }, | |
| "action_space": { | |
| ":type:": "<class 'gym.spaces.box.Box'>", | |
| ":serialized:": "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", | |
| "dtype": "float32", | |
| "_shape": [ | |
| 8 | |
| ], | |
| "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", | |
| "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", | |
| "bounded_below": "[ True True True True True True True True]", | |
| "bounded_above": "[ True True True True True True True True]", | |
| "_np_random": null | |
| }, | |
| "n_envs": 4 | |
| } |