We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\in\{1, \ldots, d\}$ follows an unknown distribution with mean $\mu_s$. In each time step, a player pulls a single arm and observes its reward. The player's goal is to identify the optimal \emph{action} $\boldsymbol{\pi}^{*} = \argmax_{\boldsymbol{\pi} \in \mathcal{A}} \boldsymbol{\mu}^{\top}\boldsymbol{\pi}$ from a finite-sized real-valued \emph{action set} $\mathcal{A}\subset \mathbb{R}^{d}$ with as few arm pulls as possible. Previous methods in the R-CPE-MAB assume that the size of the action set $\mathcal{A}$ is polynomial in $d$. We introduce an algorithm named the Generalized Thompson Sampling Explore (GenTS-Explore) algorithm, which is the first algorithm that can work even when the size of the action set is exponentially large in $d$. We also introduce a novel problem-dependent sample complexity lower bound of the R-CPE-MAB problem, and show that the GenTS-Explore algorithm achieves the optimal sample complexity up to a problem-dependent constant factor.

翻译：我们研究了多臂赌博机实值组合纯探索（R-CPE-MAB）问题。在R-CPE-MAB中，玩家面对$d$个随机臂，每个臂$s\in\{1,\ldots,d\}$的奖励服从均值$\mu_s$的未知分布。在每个时间步，玩家拉动单个臂并观察其奖励。玩家的目标是通过尽可能少的拉动次数，从有限大小的实值动作集$\mathcal{A}\subset \mathbb{R}^{d}$中识别最优动作$\boldsymbol{\pi}^{*} = \argmax_{\boldsymbol{\pi} \in \mathcal{A}} \boldsymbol{\mu}^{\top}\boldsymbol{\pi}$。现有R-CPE-MAB方法假设动作集$\mathcal{A}$的大小为$d$的多项式级。我们提出一种名为广义汤普森采样探索（GenTS-Explore）的算法，这是首个能在动作集大小随$d$指数级增长时仍能有效运行的算法。同时，我们推导了R-CPE-MAB问题的新型问题依赖样本复杂度下界，并证明GenTS-Explore算法在常数因子范围内达到了最优样本复杂度。