Optimistic Thompson Sampling for No-Regret Learning in Unknown Games

arXiv:2402.09456v1 Announce Type: new
Abstract: Many real-world problems involving multiple decision-makers can be modeled as an unknown game characterized by partial observations. Addressing the challenges posed by partial information and the curse of multi-agency, we developed Thompson sampling-type algorithms, leveraging information about opponent's action and reward structures. Our approach significantly reduces experimental budgets, achieving a more than tenfold reduction compared to baseline algorithms in practical applications like traffic routing and radar sensing. We demonstrate that, under certain assumptions about the …

abstract agency algorithms arxiv challenges cs.ai cs.lg decision game games information makers multiple sampling stat.ml type world