conditional value-at-risk for random immediate reward variables in markov decision processes条件风险价值马尔可夫决策过程的随机变量直接奖励.pdfVIP

下载本文档

3
0
约 6页
2017-08-27 发布于上海
举报
版权申诉

conditional value-at-risk for random immediate reward variables in markov decision processes条件风险价值马尔可夫决策过程的随机变量直接奖励.pdf

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

conditional value-at-risk for random immediate reward variables in markov decision processes条件风险价值马尔可夫决策过程的随机变量直接奖励

American Journal of Computational Mathematics, 2011, 1, 183-188 doi:10.4236/ajcm.2011.13021 Published Online September 2011 (http://www.SciRP.org/journal/ajcm) Conditional Value-at-Risk for Random Immediate Reward Variables in Markov Decision Processes Masayuki Kageyama, Takayuki Fujii, Koji Kanefuji, Hiroe Tsubaki The Institute of Statistical Mathematics, Tokyo, Japan E-mail : kageyama@ism.ac.jp Received May 17, 2011; revised August 10, 2011; accepted August 22, 2011 Abstract We consider risk minimization problems for Markov decision processes. From a standpoint of making the risk of random reward variable at each time as small as possible, a risk measure is introduced using condi- tional value-at-risk for random immediate reward variables in Markov decision processes, under whose risk measure criteria the risk-optimal policies are characterized by the optimality equations for the discounted or average case. As an application, the inventory models are considered. Keywords: Markov Decision Processes, Conditional Value-at-Risk, Risk Optimal Policy, Inventory Model 1. Introduction ered. In the reminder of this section, we shall establish notations that will be used throughout the paper and de- As a measure of risk for income or loss random variables, fine the problem with a new risk measure. the variance has been commonly considered since Mark- A Borel set is a Borel subset of a complete separable owitz work [1]. The variance has the shortcoming that it metric space. For a Borel set X , BX denotes the  does not approximately account for the phenomenon of