File size: 12,447 Bytes
f6dc683 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
{
"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 0x7f1a22fd3d30>",
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1a22fd3dc0>",
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1a22fd3e50>",
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1a22fd3ee0>",
"_build": "<function ActorCriticPolicy._build at 0x7f1a22fd3f70>",
"forward": "<function ActorCriticPolicy.forward at 0x7f1a22f56040>",
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1a22f560d0>",
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1a22f56160>",
"_predict": "<function ActorCriticPolicy._predict at 0x7f1a22f561f0>",
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1a22f56280>",
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1a22f56310>",
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1a22f563a0>",
"__abstractmethods__": "frozenset()",
"_abc_impl": "<_abc._abc_data object at 0x7f1a22f54900>"
},
"verbose": 1,
"policy_kwargs": {},
"observation_space": {
":type:": "<class 'gym.spaces.box.Box'>",
":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
"dtype": "float32",
"_shape": [
2
],
"low": "[-1.2 -0.07]",
"high": "[0.6 0.07]",
"bounded_below": "[ True True]",
"bounded_above": "[ True True]",
"_np_random": null
},
"action_space": {
":type:": "<class 'gym.spaces.discrete.Discrete'>",
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
"n": 3,
"_shape": [],
"dtype": "int64",
"_np_random": null
},
"n_envs": 16,
"num_timesteps": 1008000,
"_total_timesteps": 1000000,
"_num_timesteps_at_start": 0,
"seed": null,
"action_noise": null,
"start_time": 1680235032975770356,
"learning_rate": 0.0003,
"tensorboard_log": null,
"lr_schedule": {
":type:": "<class 'function'>",
":serialized:": "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"
},
"_last_obs": {
":type:": "<class 'numpy.ndarray'>",
":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAFERnb6zZ0g8ATrcvc0rST2pBGK+1mgIPI8GSL/dsBs9F4BEv8B0Bj2kRmK/K7+zvA79hD3AcEU9vBm6vmbavTv3n4u+dt5JPE+8yr6gmQg7UAZxv8mUSTzTS9a+roTsvL9Qi7/Hqdo7NG8mv+NWBb1KMdS+ox02OZG26b7iCga9lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
},
"_last_episode_starts": {
":type:": "<class 'numpy.ndarray'>",
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
},
"_last_original_obs": null,
"_episode_num": 0,
"use_sde": false,
"sde_sample_freq": -1,
"_current_progress_remaining": -0.008000000000000007,
"ep_info_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "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"
},
"ep_success_buffer": {
":type:": "<class 'collections.deque'>",
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
},
"_n_updates": 630,
"n_steps": 1000,
"gamma": 0.99,
"gae_lambda": 0.95,
"ent_coef": 0.0,
"vf_coef": 0.5,
"max_grad_norm": 0.5,
"batch_size": 64,
"n_epochs": 10,
"clip_range": {
":type:": "<class 'function'>",
":serialized:": "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"
},
"clip_range_vf": null,
"normalize_advantage": true,
"target_kl": null
} |