连续动作空间搜寻的离线强化学习轧钢机械性能软测量算法
牟俊锦, 杨春节, 贾秀凤, 李逸, 范科峰, 尹宪伟
Continuous action space exploration enabled offline reinforcement learning for mechanical property soft sensing in steel rolling processes
MU Junjin, YANG Chunjie, JIA Xiufeng, LI Yi, FAN Kefeng, YIN Xianwei
冶金自动化
.
2025, (4): 158
-166
.
DOI: 10.3969/j.issn.1000-7059.2025.04.20250187