BanditQ: Fair Bandits with Guaranteed Rewards

arXiv:2304.05219v3 Announce Type: replace
Abstract: Classic no-regret multi-armed bandit algorithms, including the Upper Confidence Bound (UCB), Hedge, and EXP3, are inherently unfair by design. Their unfairness stems from their objective of playing the most rewarding arm as frequently as possible while ignoring the rest. In this paper, we consider a fair prediction problem in the stochastic setting with a guaranteed minimum rate of accrual of rewards for each arm. We study the problem in both full-information and bandit feedback settings. …

abstract algorithms arm arxiv confidence cs.lg cs.pf design fair paper playing prediction replace rest type while