2 papers
eess.SY2025
An early termination strategy for the distributed biased min-consensus protocol under disturbances
Zicheng Huang, Wangzhi Zhou, Yuanqiu Mo
The distributed biased min-consensus (DBMC) protocol is an iterative scheme that solves the shortest path problem asymptotically, requiring only local information exchange between…
cs.MA2025
Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning
Pengcheng Dai, Yuanqiu Mo, Wenwu Yu +1
This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative…