Learning Transferable Cooperative Behavior in Multi-Agent Teams
Akshat Agarwal, Sumit Kumar, Katia Sycara, Michael Lewis
Abstract
While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. To better utilize the inherent structure of our environment, we propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other, allowing agents to selectively attend to different parts of the environment, while also introducing invariance to the number of agents or entities present in the system as well as permutation invariance. We present state-of-the-art results on coverage, formation and line control tasks for multi-agent teams in a fully decentralized execution framework.