arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.02705cs.LGstat.ML
收藏

一种有效的多变量路径规划Bandit算法

Efficient Multivariate Bandit Algorithm with Path Planning

eBay Inc.(易趣公司)

Keyu Nie, Zezhong Zhang, Ted Tao Yuan, Rong Song, Pauline Berry Burke

摘要:

本文解决了多臂强盗(Multivariate-MAB)问题中考虑臂维数层次时的臂指数爆炸问题。本文提出了一种路径规划框架(TS-PP),该框架利用决策图/树模型描述了具有m维交互的手臂奖励成功率,并采用汤普森抽样(TS)进行手臂选择的启发式搜索。自然,使用一系列过程来对抗维度灾难是非常简单的,这些过程通过关注每个过程的一个维度来顺序操作。为了我们最好的承认,我们是第一个解决多变量MAB问题,使用图路径规划策略和部署类似的蒙特卡罗树搜索的想法。我们提出的方法利用树模型相比,传统的模型,如一般的线性回归的优势。仿真结果验证了我们的要求,实现更快的收敛速度,更有效的最优手臂分配和更低的累积遗憾。

英文摘要:

In this paper, we solve the arms exponential exploding issue in multivariate Multi-Armed Bandit (Multivariate-MAB) problem when the arm dimension hierarchy is considered. We propose a framework called path planning (TS-PP) which utilizes decision graph/trees to model arm reward success rate with m-way dimension interaction, and adopts Thompson sampling (TS) for heuristic search of arm selection. Naturally, it is quite straightforward to combat the curse of dimensionality using a serial processes that operates sequentially by focusing on one dimension per each process. For our best acknowledge, we are the first to solve Multivariate-MAB problem using graph path planning strategy and deploying alike Monte-Carlo tree search ideas. Our proposed method utilizing tree models has advantages comparing with traditional models such as general linear regression. Simulation studies validate our claim by achieving faster convergence speed, better efficient optimal arm allocation and lower cumulative regret.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑