Policy invariant explicit shaping: an efficient alternative to reward shaping-MedSci.cn - 梅斯（MedSci）

Policy invariant explicit shaping: an efficient alternative to reward shaping

Behboudian, P; Satsangi, Y; Taylor, ME; Harutyunyan, A; Bowling, M

Behboudian, P (通讯作者)，Univ Alberta, Dept Comp Sci, Edmonton, AB, Canada.;Behboudian, P (通讯作者)，Alberta Machine Intelligence Inst, Edmonton, AB, Canada.

NEURAL COMPUTING & APPLICATIONS, 2022; 34 (3): 1673

科室
- - 订阅+
  - 更多科室
工具
服务