Learning in Congestion Games with Bandit Feedback. (arXiv:2206.01880v1 [cs.GT])

Learning Nash equilibria is a central problem in multi-agent systems. In this
paper, we investigate congestion games, a class of games with benign
theoretical structure and broad real-world applications. We first propose a
centralized algorithm based on the optimism in the face of uncertainty
principle for congestion games with (semi-)bandit feedback, and obtain
finite-sample guarantees. Then we propose a decentralized algorithm via a novel
combination of the Frank-Wolfe method and G-optimal design. By exploiting the
structure of the congestion game, …

arxiv congestion feedback games learning