Multi-agent Communication with Attentional and Recurrent Message Integration

Effective communication is significant for solving cooperative tasks in multi-agent domain. Agents coordinate their behaviors by appropriately modeling the communication signals or messages sent from others. To this end, agents are required to filter noise and obtain useful information from received messages, and learn to adapt to the dynamics of messages number. In this paper, we propose an attentional and recurrent message integration method (ARMI) that handles the dynamics by recurrently decoding messages, and performs attentional integration based on the relevance of each message. We evaluate our proposal on a new “predator-prey-toxin” environment where the number of agents changes, and the results outperform other competing multi-agent methods. Further investigations are also done to prove the superiority of ARMI in collaborating agents' behaviors for complex tasks and establishing interpretable communication protocol.