Learning Attentional Communication for Multi-Agent Cooperation

By Jiechuan Jiang, Zongqing Lu. 2018

609 citations recorded by the source corpus.

Communication could potentially be an effective way for multi-agent cooperation. However, information sharing among all agents or in predefined communication architectures that existing methods adopt can be problematic. When there is a large number of agents, agents cannot differentiate valuable information that helps cooperative decision making from globally shared information. Therefore, communication barely helps, and could even impair the learning of multi-agent cooperation. Predefined communication architectures, on the other hand, restrict communication among agents and thus restrain potential cooperation. To tackle these difficulties, in this paper, we propose an attentional communication model that learns when communication is needed and how to integrate shared information for cooperative decision making. Our model leads to efficient and effective communication for large-scale multi-agent cooperation. Empirically, we show the strength of our model in a variety of cooperative scenarios, where agents are able to develop more coordinated and sophisticated strategies than existing methods.

Subfields: Artificial Intelligence, Computer Networks and Communications, Sociology and Political Science, LLM Agents & Tool Use, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Sergey Levine
  3. Dacheng Tao
  4. Yoshua Bengio
  5. Trevor Darrell
  6. Ruslan Salakhutdinov
  7. Li Fei-Fei
  8. Jianfeng Gao

In Computer Networks and Communications

  1. Afshin Oroojlooyjadid
  2. Davood Hajinezhad
  3. Tonghan Wang
  4. Chongjie Zhang
  5. Xiujun Ma
  6. Yuhang Zhao
  7. Bangwei Li
  8. Yongyuan Liang

In Sociology and Political Science

  1. Davood Hajinezhad
  2. Afshin Oroojlooyjadid
  3. Xiujun Ma
  4. Yuhang Zhao
  5. Bangwei Li
  6. Yongyuan Liang
  7. Jinkyoo Park
  8. Hayong Shin

In LLM Agents & Tool Use

  1. Tonghan Wang
  2. Chongjie Zhang
  3. Davood Hajinezhad
  4. Afshin Oroojlooyjadid
  5. Bangwei Li
  6. Yongyuan Liang
  7. Xiujun Ma
  8. Yuhang Zhao

In Reinforcement Learning

  1. Chongjie Zhang
  2. Shimon Whiteson
  3. Tonghan Wang
  4. Zongqing Lu
  5. Dhruv Batra
  6. Silvio Savarese
  7. Heng Dong
  8. Jiechuan Jiang

Citations in the corpus