动态约束下可重构模块机器人分散强化学习最优控制
董博
1
, 刘克平
2
, 李元春
2
Decentralized reinforcement learning optimal control for time varying constrained reconfigurable modular robot
DONG Bo
1
, LIU Ke-ping
2
, LI Yuan-chun
2
图1 action-critic-identifier结构框图
Fig.1 Architecture of action-critic-identifier