Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies

Kaiqing Zhang, Alec Koppel, Hao Zhu 0001, Tamer Basar. Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies. SIAM J. Control and Optimization, 58(6):3586-3612, 2020. [doi]

Abstract

Abstract is missing.