Donggyu Yun, Sumyeong Ahn, A. Proutière, Jinwoo Shin, Yung Yi
{"title":"多手强盗与额外的观察","authors":"Donggyu Yun, Sumyeong Ahn, A. Proutière, Jinwoo Shin, Yung Yi","doi":"10.1145/3219617.3219639","DOIUrl":null,"url":null,"abstract":"We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. We propose algorithms that are asymptotic-optimal and order-optimal in their regrets under the settings of stochastic and adversarial rewards, respectively.","PeriodicalId":210440,"journal":{"name":"Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-armed Bandit with Additional Observations\",\"authors\":\"Donggyu Yun, Sumyeong Ahn, A. Proutière, Jinwoo Shin, Yung Yi\",\"doi\":\"10.1145/3219617.3219639\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. We propose algorithms that are asymptotic-optimal and order-optimal in their regrets under the settings of stochastic and adversarial rewards, respectively.\",\"PeriodicalId\":210440,\"journal\":{\"name\":\"Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3219617.3219639\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3219617.3219639","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. We propose algorithms that are asymptotic-optimal and order-optimal in their regrets under the settings of stochastic and adversarial rewards, respectively.