Global optimality guarantees for policy gradient methods

DOI10.1287/opre.2021.0014MaRDI QIDQ6655175

Jalaj Bhandari, Daniel J. Russo

Publication date: 20 December 2024

Published in: Operations Research (Search for Journal in Brave)

zbMATH Keywords

dynamic programmingreinforcement learningpolicy iterationpolicy gradient methodsgradient dominance

Mathematics Subject Classification ID

Mathematical programming (90Cxx)

This page was built for publication: Global optimality guarantees for policy gradient methods