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]
@article{ZhangKZB20,
title = {Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies},
author = {Kaiqing Zhang and Alec Koppel and Hao Zhu 0001 and Tamer Basar},
year = {2020},
doi = {10.1137/19M1288012},
url = {https://doi.org/10.1137/19M1288012},
researchr = {https://researchr.org/publication/ZhangKZB20},
cites = {0},
citedby = {0},
journal = {SIAM J. Control and Optimization},
volume = {58},
number = {6},
pages = {3586-3612},
}