Structural Multi-agent Learning

Kaiqian Han, Liangliang Ren, Jiwen Lu, Jie Zhou

Abstract: In this paper, we propose a multi-agent learning framework to model communication in complex multi-agent systems. Most existing multi-agent reinforcement learning methods require agents to exchange information with the environment or global manager to achieve effective and efficient interaction. We model the multi-agent system with an online adaptive graph where all agents communicate with each other through the edges. We update the graph network with a relation system which takes the current graph network and the hidden variable of agents as input. Messages and rewards are shared through the graph network. Finally, we optimize the whole system via the policy gradient algorithm. Experimental results of several multi-agent systems show the efficiency of the proposed method and its strength compared to existing methods in cooperative scenarios.

Keywords: Multi-agent Learning, Communication, Graph Network