|
|||||
|
|
An average-value-at-risk criterion for Markov decision processes with unbounded costs |
|
| Authors: | Qiuli LIU Wai-Ki CHING Junyu ZHANG Hongchu WANG |
| Affiliation: | 1. School of Mathematical Sciences, South China Normal University, Guangzhou 510631, China2. Advanced Modeling and Applied Computing Laboratory, Department of Mathematics, The University of Hong Kong, Hong Kong, China3. School of Mathematics, Sun Yat-Sen University, Guangzhou 510275, China |
| Abstract: | We study the Markov decision processes under the average-valueat-risk criterion. The state space and the action space are Borel spaces, the costs are admitted to be unbounded from above, and the discount factors are state-action dependent. Under suitable conditions, we establish the existence of optimal deterministic stationary policies. Furthermore, we apply our main results to a cash-balance model. |
| Keywords: | Markov decision processes average-value-at-risk (AVaR) stateaction dependent discount factors optimal policy |
| 点击此处可从《Frontiers of Mathematics in China》浏览原始摘要信息 | |
| 点击此处可从《Frontiers of Mathematics in China》下载全文 | |