{"title":"目标导向风险敏感马尔可夫决策过程的极端风险厌恶策略","authors":"Valdinei Freire, K. V. Delgado","doi":"10.1109/BRACIS.2016.025","DOIUrl":null,"url":null,"abstract":"The Goal-Directed Risk-Sensitive Markov Decision Process allows arbitrary risk attitudes for the probabilistic planning problem to reach a goal state. In this problem, the risk attitude is modeled by an expected exponential utility and a risk factor λ. However, the problem is not well defined for every λ, posing the problem of defining the maximum (extreme) value for this factor. In this paper, we propose an algorithm to find this e-extreme risk factor and the corresponding optimal policy.","PeriodicalId":183149,"journal":{"name":"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Extreme Risk Averse Policy for Goal-Directed Risk-Sensitive Markov Decision Process\",\"authors\":\"Valdinei Freire, K. V. Delgado\",\"doi\":\"10.1109/BRACIS.2016.025\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Goal-Directed Risk-Sensitive Markov Decision Process allows arbitrary risk attitudes for the probabilistic planning problem to reach a goal state. In this problem, the risk attitude is modeled by an expected exponential utility and a risk factor λ. However, the problem is not well defined for every λ, posing the problem of defining the maximum (extreme) value for this factor. In this paper, we propose an algorithm to find this e-extreme risk factor and the corresponding optimal policy.\",\"PeriodicalId\":183149,\"journal\":{\"name\":\"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/BRACIS.2016.025\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 5th Brazilian Conference on Intelligent Systems (BRACIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BRACIS.2016.025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Extreme Risk Averse Policy for Goal-Directed Risk-Sensitive Markov Decision Process
The Goal-Directed Risk-Sensitive Markov Decision Process allows arbitrary risk attitudes for the probabilistic planning problem to reach a goal state. In this problem, the risk attitude is modeled by an expected exponential utility and a risk factor λ. However, the problem is not well defined for every λ, posing the problem of defining the maximum (extreme) value for this factor. In this paper, we propose an algorithm to find this e-extreme risk factor and the corresponding optimal policy.