Art

J-GLOBAL ID：201702230404951185   Reference number：17A1943628

KL-UCB-Based Policy for Budgeted Multi-Armed Bandits with Stochastic Action Costs

確率的なアクションコストを伴う予算制約付き多腕バンディット問題に対するKL-UCBベースの戦略

Author (4)： WATANABE Ryo (Graduate School of Information Science and Technology, Hokkaido University) ,  KOMIYAMA Junpei (Institute of Industrial Science, The University of Tokyo) ,  NAKAMURA Atsuyoshi (Graduate School of Information Science and Technology, Hokkaido University) ,  KUDO Mineichi (Graduate School of Information Science and Technology, Hokkaido University)
Material： IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences (Web)  (IEICE Trans Fundam Electron Commun Comput Sci (Web))
Volume： E100.A  Issue： 11  Page： 2470-2486(J-STAGE)  Publication year： 2017 
JST Material Number： U0466A  ISSN： 1745-1337  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *machine learning ,  reinforcement learning ,  information use ,  information retrieval ,  *artificial intelligence ,  confidence limit
Semi thesaurus term： information utilization ,  information search ,  *AI (artificial intelligence)

Author keywords (3)： budgeted multi-armed bandits ,  asymptotically optimal policy ,  regret analysis

JST classification (1)： Artificial intelligence  (JE08000Z)

Reference (23)：

• [1] W.R. Thompson, “On the likelihood that one unknown probability exceeds another in view of the evidence of two samples,” Biometrika, vol.25, no.3-4, pp.285-294, 1933. 10.1093/biomet/25.3-4.285
• [2] H. Robbins, “Some aspects of the sequential design of experiments,” Bull. Am. Math. Soc., vol.58, no.5, pp.527-535, 1952. 10.1090/s0002-9904-1952-09620-8
• [3] L. Tran-Thanh, A. Chapman, E.M. de Cote, A. Rogers, and N.R. Jennings, “ε-first policies for budget-limited multi-armed bandits,” Proc. 24th AAAI Conference on Artificial Intelligence, pp.1211-1216, 2010.
• [4] L. Tran-Thanh, A. Rogers, A. Chapman, and N.R. Jennings, “Knapsack based optimal policies for budget-limited multi-armed bandits,” Proc. 26th AAAI Conference on Artifical Intelligence, pp.1134-1140, 2012.
• [5] W. Ding, T. Qin, X.D. Zhang, and T.Y. Liu, “Multi-armed bandit with budget constraint and variable costs,” Proc. 27th AAAI Conference on Artificial Intelligence, pp.232-238, 2013.

Terms in the title (6)： 確率 ,  アクション ,  予算 ,  制約 ,  腕 ,  戦略