BriefGPT.xyz
Oct, 2020
神经汤普森抽样
Neural Thompson Sampling
HTML
PDF
Weitong Zhang, Dongruo Zhou, Lihong Li, Quanquan Gu
TL;DR
本文介绍了一种基于深度神经网络和贝叶斯推断的新型算法——神经 Thompson Sampling(Neural Thompson Sampling),并证明该算法的性能能够和同类算法相匹配,实验结果证实了该理论。
Abstract
thompson sampling
(TS) is one of the most effective algorithms for solving contextual
multi-armed bandit
problems. In this paper, we propose a new algorithm, called Neural
→