用户名: 密码: 验证码:
Trading performance for stability in Markov decision processes
详细信息    查看全文
文摘

We show that optimizing mean payoff and stability requires memory and randomization.

We show how to reduce existence of optimal strategies to a constrained problem.

We give a complexity classification for the problem of finding an optimal strategy.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700