Jul 2026
Two-Stage Homotopic Learning for Data-Driven Cluster Consensus in Multiagent Systems.
A novel homotopic reinforcement learning (RL) framework is proposed to address the distributed cluster consensus problem in continuous-time multiagent systems (MASs) as a zero-sum differential game using a proposed minmax game policy.
Qing Yang, Jing Wang, Jinde Cao et al.
· IEEE Transactions on Cyberne... · 0 citations