Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/190921
Title: R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
Authors: ZHONGXIANG DAI 
Yizhou Chen
Bryan Kian Hsiang Low
Patrick Jaillet
HO TECK HUA 
Issue Date: 30-Jun-2020
Citation: ZHONGXIANG DAI, Yizhou Chen, Bryan Kian Hsiang Low, Patrick Jaillet, HO TECK HUA (2020-06-30). R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games. Proceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020.. ScholarBank@NUS Repository.
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Abstract: This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff functions in repeated games, which we call Recursive Reasoning-Based BO (R2-B2). Our R2-B2 algorithm is general in that it does not constrain the relationship among the payoff functions of different agents and can thus be applied to various types of games such as constant-sum, general-sum, and common-payoff games. We prove that by reasoning at level 2 or more and at one level higher than the other agents, our R2-B2 agent can achieve faster asymptotic convergence to no regret than that without utilizing recursive reasoning. We also propose a computationally cheaper variant of R2-B2 called R2-B2-Lite at the expense of a weaker convergence guarantee. The performance and generality of our R2-B2 algorithm are empirically demonstrated using synthetic games, adversarial machine learning, and multi-agent reinforcement learning.
Source Title: Proceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020.
URI: https://scholarbank.nus.edu.sg/handle/10635/190921
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
R2-B2 Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games.pdf4.37 MBAdobe PDF

OPEN

PublishedView/Download

Page view(s)

150
checked on Jan 26, 2023

Download(s)

2
checked on Jan 26, 2023

Google ScholarTM

Check


This item is licensed under a Creative Commons License Creative Commons