2023
Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits
NeurIPS 2023poster
We study pure exploration with infinitely many bandit arms generated \iid from an unknown distribution. Our goal is to efficiently select a single high quality arm whose average reward is, with probability $1-\delta$, within $\varepsilon$ of being with the top $\eta$-fraction of arms; this is a natu…