Continuity of the Value of Competitive Markov Decision Processes
Continuity of the Value of Competitive Markov Decision Processes
复制标题
竞争性马尔可夫决策过程价值的连续性
DOI：
10.1023/b:jotp.0000011995.28536.ef
复制
发表时间：
2003
影响因子：
0.8
通讯作者：
Eilon Solan
中科院分区：
文献类型：
--
作者：
Eilon Solan
我们给出了赋给每个竞争马尔可夫决策过程的函数及其折扣值的一个上界。这个界意味着竞争马尔可夫决策过程的未折扣值在转移规则空间的相对内部是连续的。
We provide a bound for the variation of the function that assigns to every competitive Markov decision process and every discount factor its discounted value. This bound implies that the undiscounted value of a competitive Markov decision process is continuous in the relative interior of the space of transition rules.