Multi-Agent Communication With Attentional And Recurrent Message Integration
2018 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (ISCC)(2018)
摘要
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.
更多查看译文
关键词
multi-agent reinforcement learning, recurrent message integration, attention mechanism
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络