Best Arm Identification for Bandits with Shifting Means
Advances theoretical ML research on sequential decision-making under non-stationary environments with rigorous mathematical analysis.
AI Summary
Researchers propose a new algorithm called ISM for best arm identification in bandits with adversarial shifting means, proving theoretical guarantees and matching lower bounds.
Excerpt
We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means. While classically the mean rewards of the $K$ arms are stable in time, in Shifting Means only the gaps $\boldsymbolΔ$ between mean rewards are stable, while their common shift may be determined adversarially in each round. The objective of the learner is to identify the best arm with high probability while minimizing sample complexity (the fixed c