Regret-Based Multi-Agent Coordination with Uncertain Task Rewards

Many multi-agent coordination problems can be represented as DCOPs. Motivated by task allocation in disaster response, we extend standard DCOP models to consider uncertain task rewards where the outcome of completing a task depends on its current state, which is randomly drawn from unknown dis-tributions. The goal of solving this problem is to find a solu-tion for all agents that minimizes the overall worst-case loss. This is a challenging problem for centralized algorithms be-cause the search space grows exponentially with the number of agents and is nontrivial for existing algorithms for standard DCOPs. To address this, we propose a novel decentralized al-gorithm that incorporates Max-Sum with iterative constraint generation to solve the problem by passing messages among agents. By so doing, our approach scales well and can solve instances of the task allocation problem with hundreds of a-gents and tasks