arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.06982stat.MLcs.LGecon.EMstat.ME
收藏

基于Bandit算法的相依样本离政策评估的置信区间--标准鞅方法

Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales

CyberAgent Inc.(赛博艾坚特公司)

Masahiro Kato

摘要:

本研究针对由bandit演算法所得到的相依样本,提出一个离政策评估(OPE)的问题。OPE的目标是评估一个新的策略使用的历史数据从行为策略产生的强盗算法。由于bandit算法根据过去的观察结果更新策略,因此样本不是独立和同分布(i.i.d.)的。然而,用于OPE的几种现有方法没有考虑这个问题,并且基于样本是i.i.d.的假设。在这项研究中,我们解决这个问题,通过构建一个估计从一个标准化的鞅差序列。为了标准化序列,我们考虑使用评估数据或样本分裂两步估计。这种方法产生的估计渐近正态性,而不限制一类行为的政策。在一个实验中,所提出的估计比现有的方法,它假设的行为策略收敛到一个时不变的政策表现得更好。

英文摘要:

This study addresses the problem of off-policy evaluation (OPE) from dependent samples obtained via the bandit algorithm. The goal of OPE is to evaluate a new policy using historical data obtained from behavior policies generated by the bandit algorithm. Because the bandit algorithm updates the policy based on past observations, the samples are not independent and identically distributed (i.i.d.). However, several existing methods for OPE do not take this issue into account and are based on the assumption that samples are i.i.d. In this study, we address this problem by constructing an estimator from a standardized martingale difference sequence. To standardize the sequence, we consider using evaluation data or sample splitting with a two-step estimation. This technique produces an estimator with asymptotic normality without restricting a class of behavior policies. In an experiment, the proposed estimator performs better than existing methods, which assume that the behavior policy converges to a time-invariant policy.

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。

↑