Global Convergence of Policy Gradient for Linear-Quadratic
Mean-Field Control/Game in Continuous Time
Weichen Wang 1 Jiequn Han 2 Zhuoran Yang 3 Zhaoran Wang 4
Abstract more realistic real-world problems, such as robotic control
(Yang & Gu, 2004), autonomous driving (Shalev-Shwartz
Recent years have witnessed the success of multi-
et al., 2016), and social dilemmas ( ...


雷达卡




京公网安备 11010802022788号







