Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs
This solves a key trade-off in distributed learning for multi-agent systems, enabling efficient collaboration with minimal communication overhead.
The paper tackles the problem of cooperative multi-agent bandits by developing an algorithm that achieves optimal individual regret and constant communication costs, addressing limitations in prior leader-follower and fully distributed approaches.
Recently, there has been extensive study of cooperative multi-agent multi-armed bandits where a set of distributed agents cooperatively play the same multi-armed bandit game. The goal is to develop bandit algorithms with the optimal group and individual regrets and low communication between agents. The prior work tackled this problem using two paradigms: leader-follower and fully distributed algorithms. Prior algorithms in both paradigms achieve the optimal group regret. The leader-follower algorithms achieve constant communication costs but fail to achieve optimal individual regrets. The state-of-the-art fully distributed algorithms achieve optimal individual regrets but fail to achieve constant communication costs. This paper presents a simple yet effective communication policy and integrates it into a learning algorithm for cooperative bandits. Our algorithm achieves the best of both paradigms: optimal individual regret and constant communication costs.