Strategizing against Learners in Bayesian Games

被引:0
|
作者
Mansour, Yishay [1 ,2 ]
Mohri, Mehryar [2 ,3 ]
Schneider, Jon [2 ]
Sivan, Balasubramanian [2 ]
机构
[1] Tel Aviv Univ, Blavatnik Sch Comp Sci, Tel Aviv, Israel
[2] Google Res, Mountain View, CA 94043 USA
[3] Courant Inst Math Sci, New York, NY USA
来源
基金
欧洲研究理事会; 以色列科学基金会;
关键词
Stackelberg value; swap regret; Bayesian games;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer. We consider general Bayesian games, where the payoffs of both the optimizer and the learner could depend on the type, which is drawn from a publicly known distribution, but revealed privately to the learner. We address the following questions: (a) what is the bare minimum that the optimizer can guarantee to obtain regardless of the no-regret learning algorithm employed by the learner? (b) are there learning algorithms that cap the optimizer payoff at this minimum? (c) can these algorithms be implemented efficiently? While building this theory of optimizer-learner interactions, we define a new combinatorial notion of regret called polytope swap regret, that could be of independent interest in other settings.
引用
收藏
页数:32
相关论文
共 50 条
  • [1] Strategizing against No-regret Learners
    Deng, Yuan
    Schneider, Jon
    Sivan, Balasubramanian
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [2] Strategizing Against Q-Learners: A Control-Theoretical Approach
    Arslantas, Yuksel
    Yuceel, Ege
    Sayin, Muhammed O.
    IEEE CONTROL SYSTEMS LETTERS, 2024, 8 : 1733 - 1738
  • [3] Tangible insights on the strategizing of language learners and users
    Cohen, Andrew D.
    Gu, Peter Yongqi
    Nyikos, Martha
    Plonsky, Luke
    Harris, Vee
    Gunning, Pamela
    Wang, Isobel Kai-Hui
    Pawlak, Miroslaw
    Gavriilidou, Zoe
    Mitits, Lydia
    Sykes, Julie M.
    Gao, Xuesong
    LANGUAGE TEACHING, 2023, 56 (03) : 313 - 332
  • [4] STRATEGIZING INCLUSIVITY IN TEACHING DIVERSE LEARNERS IN HIGHER EDUCATION
    Awang-Hashim, Rosna
    Kaur, Amrita
    Valdez, Nena P.
    MALAYSIAN JOURNAL OF LEARNING & INSTRUCTION, 2019, 16 (01): : 105 - 128
  • [5] Is Learning in Games Good for the Learners?
    Brown, William
    Schneider, Jon
    Vodrahalli, Kiran
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [6] STREET GAMES AND TRADITIONAL GAMES FOR EARLY LEARNERS - THAKKAR,A
    SRINIVASAN, N
    INDIAN JOURNAL OF SOCIAL WORK, 1989, 50 (04): : 559 - 561
  • [7] Ambiguous Bayesian Games
    Zhang, Youzhi
    Luo, Xudong
    Ma, Wenjun
    Leung, Ho-fung
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2014, 29 (12) : 1138 - 1172
  • [8] A Note on Bayesian Games
    Liu, Yang
    LOGIC, RATIONALITY, AND INTERACTION (LORI 2013), 2013, 8196 : 326 - 331
  • [9] Bayesian Games with Intentions
    Bjorndahl, Adam
    Halpern, Joseph Y.
    Pass, Rafael
    ELECTRONIC PROCEEDINGS IN THEORETICAL COMPUTER SCIENCE, 2016, (215): : 99 - 113
  • [10] Bayesian games with intentions
    Bjorndahl, Adam
    Halpern, Joseph Y.
    Pass, Rafael
    GAMES AND ECONOMIC BEHAVIOR, 2020, 123 : 54 - 67