Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

40 行
1.0 KiB

behaviors:
FoodCollector:
trainer_type: ppo
hyperparameters:
batch_size: 64
buffer_size: 10240
learning_rate: 0.0003
beta: 0.005
epsilon: 0.2
lambd: 0.95
num_epoch: 3
learning_rate_schedule: linear
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
vis_encode_type: simple
reward_signals:
gail:
gamma: 0.99
strength: 0.1
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
vis_encode_type: simple
learning_rate: 0.0003
use_actions: false
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
summary_freq: 10000
threaded: true
behavioral_cloning:
demo_path: Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
steps: 0
strength: 1.0
samples_per_update: 0