Using Communication to Reduce Locality in Multi-Robot Learning

This paper attempts to bridge the elds of machine learning, robotics, and distributed AI. It discusses the use of communication in reducing the undesirable eeects of locality in fully distributed multi-agent systems with multiple agents/robots learning in parallel while interacting with each other. Two key problems, hidden state and credit assignment, are addressed by applying local undirected broadcast communication in a dual role: as sensing and as reinforcement. The methodology is demonstrated on two multi-robot learning experiments. The rst describes learning a tightly-coupled coordination task with two robots, the second a loosely-coupled task with four robots learning social rules. Communication is used to share sensory data to overcome hidden state and reinforcement to overcome the credit assignment problem between the agents and to bridge the gap between local and global payoo.