Approximate Difference Rewards for Scalable Multigent Reinforcement Learning

We address the problem of multiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains-air-traffic control and cooperative navigation, shows better solution quality than previous approaches.