Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity

DOI10.1007/s10107-023-02017-4MaRDI QIDQ6608040

Yan Li, Guanghui Lan, Tuo Zhao

Publication date: 19 September 2024

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

zbMATH Keywords

sample complexitypolicy convergencelocal accelerationpolicy gradient method

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Nonconvex programming, global optimization (90C26) Stochastic programming (90C15) Markov and semi-Markov decision processes (90C40)

This page was built for publication: Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity