BriefGPT.xyz
Oct, 2016
乐观主义的终结？有限臂线性赌博机的渐近分析
The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits
HTML
PDF
Tor Lattimore, Csaba Szepesvari
TL;DR
这篇研究分析了随机线性赌博机在实例依赖性遗憾方面的异步情况，并得出了最优性的上下界匹配结果，表明基于乐观主义或汤普森抽样的算法将永远无法达到最优速度，甚至在非常简单的情况下也可能与最优解相差无几。
Abstract
stochastic linear bandits
are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notably the
→