Convergence of entropy-regularized natural policy gradient with linear function approximation

DOI10.1137/22M1540156MaRDI QIDQ6587339FDOQ6587339

Authors: Semih Cayci, Niao He, R. Srikant 

Publication date: 14 August 2024

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

nonconvex optimizationreinforcement learningpolicy gradient

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Graph theory (including graph drawing) in computer science (68R10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites Work

• Understanding machine learning. From theory to algorithms
• Title not available (Why is that?)
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Natural actor-critic algorithms
• An analysis of temporal-difference learning with function approximation
• Reinforcement learning. An introduction
• Asymptotic evaluation of certain markov process expectations for large time. IV
• Algorithms for reinforcement learning.
• Random design analysis of ridge regression
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

This page was built for publication: Convergence of entropy-regularized natural policy gradient with linear function approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587339)