An Optimal Rewiring Strategy for Cooperative Multiagent Social Learning


  • Hongyao Tang Tianjin University
  • Jianye Hao Tianjin University
  • Li Wang Tianjin University
  • Tim Baarslag Netherlands Organisation for Scientific Research
  • Zan Wang Tianjin University



Multiagent coordination in cooperative multiagent systems (MASs) has been widely studied in both fixed-agent repeated interaction setting and static social learning framework. However, two aspects of dynamics in real-world MASs are currently missing. First, the network topologies can dynamically change during the course of interaction. Second, the interaction utilities between each pair of agents may not be identical and not known as a prior. Both issues mentioned above increase the difficulty of coordination. In this paper, we consider the multiagent social learning in a dynamic environment in which agents can alter their connections and interact with randomly chosen neighbors with unknown utilities beforehand. We propose an optimal rewiring strategy to select most beneficial peers to maximize the accumulated payoffs in long-run interactions. We empirically demonstrate the effects of our approach in large-scale MASs.




How to Cite

Tang, H., Hao, J., Wang, L., Baarslag, T., & Wang, Z. (2019). An Optimal Rewiring Strategy for Cooperative Multiagent Social Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 10049-10050.



Student Abstract Track