Variance-reduced conservative policy iteration

MaRDI QIDQ7022774zbMATH OpenFDO

Authors Naman Agarwal, Brian Bullins, Karan Singh

Publication date 24 February 2025

Full work available at URL https://proceedings.mlr.press/v201/agarwal23a.html

zbMATH Keywords

non-convex optimizationreinforcement learningvariance reduction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonconvex programming, global optimization (90C26)

Cites work

• Finite-time bounds for fitted value iteration
• Katyusha: the first direct acceleration of stochastic gradient methods
• Minimizing finite sums with the stochastic average gradient
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Variance-reduced conservative policy iteration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7022774)