Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, Max F. Kramer
{"title":"人工智能的道德决策框架","authors":"Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, Max F. Kramer","doi":"10.1609/aaai.v31i1.11140","DOIUrl":null,"url":null,"abstract":"\n \n The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for finding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.\n \n","PeriodicalId":354113,"journal":{"name":"International Symposium on Artificial Intelligence and Mathematics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"145","resultStr":"{\"title\":\"Moral Decision Making Frameworks for Artificial Intelligence\",\"authors\":\"Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, Max F. Kramer\",\"doi\":\"10.1609/aaai.v31i1.11140\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n \\n The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for finding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.\\n \\n\",\"PeriodicalId\":354113,\"journal\":{\"name\":\"International Symposium on Artificial Intelligence and Mathematics\",\"volume\":\"25 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-02-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"145\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Symposium on Artificial Intelligence and Mathematics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1609/aaai.v31i1.11140\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Symposium on Artificial Intelligence and Mathematics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/aaai.v31i1.11140","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Moral Decision Making Frameworks for Artificial Intelligence
The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for finding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
