BriefGPT.xyz
Jul, 2024
开放问题：Bernoulli奖励的核化多臂赌博机紧密界限
Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards
HTML
PDF
Marco Mussi, Simone Drago, Alberto Maria Metelli
TL;DR
该研究论文讨论了核化赌博机在观测到服从伯努利分布的实现时的优化问题，并提出了相应的开放性问题。
Abstract
We consider
kernelized bandits
(KBs) to optimize a function $f : \mathcal{X} \rightarrow [0,1]$ belonging to the
reproducing kernel hilbert space
(RKHS) $\mathcal{H}_k$. Mainstream works on
→