Communication in Multi-Agent Reinforcement Learning: Intention Sharing

WOOJUN KIM · Jongeui Park · Youngchul Sung

Keywords: [ communication ] [ attention ] [ multi-agent reinforcement learning ] [ intention ]

[ Abstract ]
[ Paper ]
Wed 5 May 1 a.m. PDT — 3 a.m. PDT


Communication is one of the core components for learning coordinated behavior in multi-agent systems. In this paper, we propose a new communication scheme named Intention Sharing (IS) for multi-agent reinforcement learning in order to enhance the coordination among agents. In the proposed IS scheme, each agent generates an imagined trajectory by modeling the environment dynamics and other agents' actions. The imagined trajectory is the simulated future trajectory of each agent based on the learned model of the environment dynamics and other agents and represents each agent's future action plan. Each agent compresses this imagined trajectory capturing its future action plan to generate its intention message for communication by applying an attention mechanism to learn the relative importance of the components in the imagined trajectory based on the received message from other agents. Numeral results show that the proposed IS scheme outperforms other communication schemes in multi-agent reinforcement learning.

Chat is not available.