From Few to More: Large-Scale Dynamic Multiagent Curriculum Learning


  • Weixun Wang Tianjin University
  • Tianpei Yang Tianjin University
  • Yong Liu Nanjing University
  • Jianye Hao Tianjin University
  • Xiaotian Hao Tianjin University
  • Yujing Hu NetEase Fuxi AI Lab
  • Yingfeng Chen NetEase Fuxi AI Lab
  • Changjie Fan NetEase Fuxi AI Lab
  • Yang Gao Nanjing University



A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale multiagent settings due to the complex dynamics between the environment and agents and the explosion of state-action space. In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents. We propose three transfer mechanisms across curricula to accelerate the learning process. Moreover, due to the fact that the state dimension varies across curricula, and existing network structures cannot be applied in such a transfer setting since their network input sizes are fixed. Therefore, we design a novel network structure called Dynamic Agent-number Network (DyAN) to handle the dynamic size of the network input. Experimental results show that DyMA-CL using DyAN greatly improves the performance of large-scale multiagent learning compared with state-of-the-art deep reinforcement learning approaches. We also investigate the influence of three transfer mechanisms across curricula through extensive simulations.




How to Cite

Wang, W., Yang, T., Liu, Y., Hao, J., Hao, X., Hu, Y., Chen, Y., Fan, C., & Gao, Y. (2020). From Few to More: Large-Scale Dynamic Multiagent Curriculum Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7293-7300.



AAAI Technical Track: Multiagent Systems