sir-model/config.yml at master · poehlerflorian/sir-model · GitHub

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
100
101
102
103
104
105
106
107
108
109
110
111
112
behaviors:
  normal:
    trainer_type: ppo
    hyperparameters:
      learning_rate: 0.001
      learning_rate_schedule: linear
      batch_size: 1024
      buffer_size: 50000
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
    network_settings:
      normalize: false
      hidden_units: 128
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.8
        strength: 1.0
    keep_checkpoints: 5
    checkpoint_interval: 50000
    max_steps: 5000000
    time_horizon: 64
    summary_freq: 10000
    threaded: true

  extroverted:
    trainer_type: ppo
    hyperparameters:
      learning_rate: 0.001
      learning_rate_schedule: linear
      batch_size: 1024
      buffer_size: 50000
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
    network_settings:
      normalize: false
      hidden_units: 128
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.8
        strength: 1.0
    keep_checkpoints: 5
    checkpoint_interval: 50000
    max_steps: 5000000
    time_horizon: 64
    summary_freq: 10000
    threaded: true

  introverted:
    trainer_type: ppo
    hyperparameters:
      learning_rate: 0.001
      learning_rate_schedule: linear
      batch_size: 1024
      buffer_size: 50000
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
    network_settings:
      normalize: false
      hidden_units: 128
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.8
        strength: 1.0
    keep_checkpoints: 5
    checkpoint_interval: 50000
    max_steps: 5000000
    time_horizon: 64
    summary_freq: 10000
    threaded: true

  medic:
    trainer_type: ppo
    hyperparameters:
      learning_rate: 0.0003
      learning_rate_schedule: linear
      batch_size: 1024
      buffer_size: 8192
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 8
    network_settings:
      normalize: false
      hidden_units: 512
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.99
        strength: 1.0
      curiosity:
        strength: 0.02
        gamma: 0.99
        encoding_size: 256
    keep_checkpoints: 5
    checkpoint_interval: 100000
    max_steps: 7000000
    time_horizon: 64
    summary_freq: 1000
    threaded: true