Multi-Agent Coordination via Multi-Level Communication

Ziluo Ding, Zeyuan Liu, Zhirui Fang, Kefan Su, Liwen Zhu, Zongqing Lu

Keywords: multi-agent reinforcement learning

TL;DR: We propose SeqComm, a multi-agent communication scheme that enhances coordination by prioritizing actions and communication.

Abstract: The partial observability and stochasticity in multi-agent settings can be mitigated by accessing more information about others via communication. However, the coordination problem still exists since agents cannot communicate actual actions with each other at the same time due to the circular dependencies. In this paper, we propose a novel multi-level communication scheme, Sequential Communication (SeqComm). SeqComm treats agents asynchronously (the upper-level agents make decisions before the lower-level ones) and has two communication phases. In the negotiation phase, agents determine the priority of decision-making by communicating hidden states of observations and comparing the value of intention, which is obtained by modeling the environment dynamics. In the launching phase, the upper-level agents take the lead in making decisions and then communicate their actions with the lower-level agents. Theoretically, we prove the policies learned by SeqComm are guaranteed to improve monotonically and converge. Empirically, we show that SeqComm outperforms existing methods in a variety of cooperative multi-agent tasks.

Primary Area: Reinforcement learning

Submission Number: 3961