File size: 13,358 Bytes
63f213e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9537354
 
63f213e
 
 
9537354
63f213e
 
 
 
9537354
63f213e
 
 
 
 
 
 
 
 
9537354
63f213e
 
 
9537354
63f213e
 
 
 
 
9537354
63f213e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
96
97
98
99
{
    "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 0x7d2fe0dac280>",
        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2fe0dac310>",
        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2fe0dac3a0>",
        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2fe0dac430>",
        "_build": "<function ActorCriticPolicy._build at 0x7d2fe0dac4c0>",
        "forward": "<function ActorCriticPolicy.forward at 0x7d2fe0dac550>",
        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2fe0dac5e0>",
        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2fe0dac670>",
        "_predict": "<function ActorCriticPolicy._predict at 0x7d2fe0dac700>",
        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2fe0dac790>",
        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2fe0dac820>",
        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2fe0dac8b0>",
        "__abstractmethods__": "frozenset()",
        "_abc_impl": "<_abc._abc_data object at 0x7d2fe0d3d4c0>"
    },
    "verbose": 1,
    "policy_kwargs": {},
    "num_timesteps": 1000448,
    "_total_timesteps": 1000000,
    "_num_timesteps_at_start": 0,
    "seed": null,
    "action_noise": null,
    "start_time": 1734119153880577099,
    "learning_rate": 0.0003,
    "tensorboard_log": null,
    "_last_obs": {
        ":type:": "<class 'numpy.ndarray'>",
        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAIZgBT44o5i7j/2kOzTxB7rGYty8XcfougAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
    },
    "_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": -0.00044800000000000395,
    "_stats_window_size": 100,
    "ep_info_buffer": {
        ":type:": "<class 'collections.deque'>",
        ":serialized:": "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"
    },
    "ep_success_buffer": {
        ":type:": "<class 'collections.deque'>",
        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
    },
    "_n_updates": 4300,
    "observation_space": {
        ":type:": "<class 'gymnasium.spaces.box.Box'>",
        ":serialized:": "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",
        "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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"
    }
}