Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs

We study the multi-agent multi-armed bandit (MAMAB) problem, where m agents are factored into ρ overlapping groups. Each group represents a hyperedge, forming a hypergraph over the agents. At each round of interaction, the learner pulls a joint arm (composed of individual arms for each agent) and receives a reward according to the hypergraph structure. Specifically, we assume there is a local reward for each hyperedge, and the reward of the joint arm is the sum of these local rewards. Previous work introduced the multi-agent Thompson sampling (MATS) algorithm (Verstraeten et al. 2020) and derived a Bayesian regret bound. However, it remains an open problem how to derive a frequentist regret bound for Thompson sampling in this multiagent setting. To address these issues, we propose an efficient variant of MATS, the ϵ-exploring Multi-Agent Thompson Sampling (ϵ-MATS) algorithm, which performs MATS exploration with probability ϵ while adopts a greedy policy otherwise. We prove that ϵ-MATS achieves a worst-case frequentist regret bound that is sublinear in both the time horizon and the local arm size. We also derive a lower bound for this setting, which implies our frequentist regret upper bound is optimal up to constant and logarithm terms, when the hypergraph is sufficiently sparse. Thorough experiments on standard MAMAB problems demonstrate the superior performance and the improved computational efficiency of ϵ-MATS compared with existing algorithms in the same setting.