Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes
2024 IEEE 18TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION, ICCA 2024（2024）
关键词
Dynamic Programming,Markov Decision Process,Multi-agent Markov Decision Process,Communication Network,Convergence Of Algorithm,Distributed Algorithm,Control Perspective,Distributed Learning,Temporal Learning,Value Function,Transition State,Diagonal Matrix,Results Of This Paper,Undirected,Global Status,Weight Vector,Equilibrium Point,Control Theory,Asymptotically Stable,Temporal Difference Learning,Finite State Space,Joint Policy,Auxiliary Vector,Joint Action,Graph Laplacian,Reward Function,Matrix Notation,Stochastic Policy
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要