基于正交投影的同态状态抽象与策略优化
赵亮,李永强,赵硕

Homomorphic state abstraction and policy optimization based on orthogonal projection
Liang ZHAO,Yongqiang LI,Shuo ZHAO
图 3 本文方法与 EBHPG 在不同任务下的性能及下界差异对比
Fig.3 Comparison of performance and lower bound difference between proposed method and EBHPG under different tasks