Coordinated Learning for Loosely Coupled Agents with Sparse Interactions

Multiagent learning is a challenging problem in the area of multiagent systems because of the non-stationary environment caused by the interdependencies between agents. Learning for coordination becomes more difficult when agents do not know the structure of the environment and have only local observability. In this paper, an approach is proposed to enable autonomous agents to learn where and how to coordinate their behaviours in an environment where the interactions between agents are sparse. Our approach firstly adopts a statistical method to detect those states where coordination is most necessary. A Q-learning based coordination mechanism is then applied to coordinate agents’ behaviours based on their local observability of the environment. We test our approach in grid world domains to show its good performance.