UVIP: model-free approach to evaluate reinforcement learning algorithms

DOI10.1007/S10957-025-02903-1MaRDI QIDQ6849471zbMATH OpenFDO

Authors D. Belomestny, Ilya Levin, Alexey Naumov, S. P. Samsonov

Publication date 5 March 2026

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10957-025-02903-1

zbMATH Keywords

model-free algorithmpolicy errorpolicy evaluationreinforcement learningtight confidence intervals for optimal value function

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Markov and semi-Markov decision processes (90C40)

Cites work

• Advanced simulation-based methods for optimal stopping and control. With applications in finance
• Algorithms for reinforcement learning.
• Expected policy gradients for reinforcement learning
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• Interpolation of Lipschitz functions
• Locally contracting iterated functions and stability of Markov chains
• Markov Chains
• Near-optimal regret bounds for reinforcement learning
• On the Generation of Markov Decision Processes
• Pathwise Stochastic Optimal Control
• Practical kernel-based reinforcement learning
• Reinforcement learning. An introduction
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• The covering radius of randomly distributed points on a manifold

This page was built for publication: UVIP: model-free approach to evaluate reinforcement learning algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6849471)