arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.05660cs.LGmath.STstat.TH
收藏

Bandit算法的典型行为

The Typical Behavior of Bandit Algorithms

Stanford University(斯坦福大学)

Lin Fan, Peter W. Glynn

摘要:

我们建立了强大数定律和中心极限定理的遗憾的两个最流行的强盗算法:汤普森采样和UCB。在这里,我们对遗憾分布的描述补充了Fan和Glynn(2021)(arXiv:2109.13595)最近开发的遗憾分布尾部的描述。尾部特征与轨迹上的非典型强盗行为相关,其中最佳臂均值被低估,导致最佳臂的错误识别和大的遗憾。相反,我们的SLLN和CLT在这里描述了典型的行为和波动的轨迹上的最佳手臂平均值是正确估计的遗憾。我们发现,汤普森采样和UCB满足相同的SLLN和CLT,与SLLN和(平均)在CLT中心序列的渐近匹配的渐近预期后悔。CLT的均值和方差均随着时间范围$T$以$\log(T)$的速率增长。渐近地作为$T \to \infty$,每个次优臂的游戏次数的可变性仅取决于该臂接收的奖励,这表明每个次优臂独立地对总体CLT方差做出贡献。

英文摘要:

We establish strong laws of large numbers and central limit theorems for the regret of two of the most popular bandit algorithms: Thompson sampling and UCB. Here, our characterizations of the regret distribution complement the characterizations of the tail of the regret distribution recently developed by Fan and Glynn (2021) (arXiv:2109.13595). The tail characterizations there are associated with atypical bandit behavior on trajectories where the optimal arm mean is under-estimated, leading to mis-identification of the optimal arm and large regret. In contrast, our SLLN's and CLT's here describe the typical behavior and fluctuation of regret on trajectories where the optimal arm mean is properly estimated. We find that Thompson sampling and UCB satisfy the same SLLN and CLT, with the asymptotics of both the SLLN and the (mean) centering sequence in the CLT matching the asymptotics of expected regret. Both the mean and variance in the CLT grow at $\log(T)$ rates with the time horizon $T$. Asymptotically as $T \to \infty$, the variability in the number of plays of each sub-optimal arm depends only on the rewards received for that arm, which indicates that each sub-optimal arm contributes independently to the overall CLT variance.

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。

↑