CSpace

浏览/检索结果: 共4条,第1-4条 帮助

已选(0)清除 条数/页:   排序方式:
On average reward semi-markov decision processes with a general multichain structure 期刊论文
MATHEMATICS OF OPERATIONS RESEARCH, 2004, 卷号: 29, 期号: 2, 页码: 339-352
作者:  Jianyong, L;  Xiaobo, Z
收藏  |  浏览/下载:90/0  |  提交时间:2018/07/30
semi-Markov decision processes  average reward criterion  multichain structure  data-transformation method  optimal policy  
Notes on average Markov decision processes with a minimum-variance criterion 期刊论文
OPERATIONS RESEARCH LETTERS, 2002, 卷号: 30, 期号: 2, 页码: 107-116
作者:  Liu, JY
收藏  |  浏览/下载:76/0  |  提交时间:2018/07/30
Markov decision processes  nonstationary MDP  average criterion  variance criterion  strong variance optimal policy  
Weighted Markov decision processes with perturbation 期刊论文
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2001, 卷号: 53, 期号: 3, 页码: 465-480
作者:  Liu, K;  Filar, JA
收藏  |  浏览/下载:148/0  |  提交时间:2018/07/30
Markov decision processes  weighted reward  optimal policy  delta-optimal  singular perturbation  general perturbation  
Nonhomogeneous Markov decision processes with Borel state space - The average criterion with nonuniformly bounded rewards 期刊论文
MATHEMATICS OF OPERATIONS RESEARCH, 2000, 卷号: 25, 期号: 4, 页码: 667-678
作者:  Guo, XP;  Liu, JY;  Liu, K
收藏  |  浏览/下载:119/0  |  提交时间:2018/07/30
nonhomogeneous Markov decision processes  average reward criterion  optimality equations  epsilon(>= 0)-optimal policies  rolling horizon algorithm