Unity_mlagents_Robot_arm/trainer_config.yaml at main · ChaejungMaeng/Unity_mlagents_Robot_arm · 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
behaviors:
    default:
        trainer_type: ppo
        hyperparameters:
            batch_size: 256
            buffer_size: 2560
            learning_rate_schedule: linear
            learning_rate: 3.0e-4
        network_settings:
            hidden_units: 256
            normalize: false
            num_layers: 3
            vis_encode_type: simple
            memory:
                memory_size: 256
                sequence_length: 256
        max_steps: 10.0e5
        time_horizon: 64
        summary_freq: 10000
        reward_signals:
            extrinsic:
                strength: 1.0
                gamma: 0.99
    Robotarm:
        trainer_type: ppo
        hyperparameters:
            batch_size: 256
            buffer_size: 2560
        network_settings:
            hidden_units: 256
            num_layers: 3
        max_steps: 10.0e6
        time_horizon: 128