Optimal approximation of average reward Markov decision processes

DOI10.1134/S0965542524702191MaRDI QIDQ6986214zbMATH OpenFDO

Authors Y. F. Sapronov, N. E. Yudin

Publication date 12 May 2025

Published in Computational Mathematics and Mathematical Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/S0965542524702191

zbMATH Keywords

ICOMP2024iteration complexityMarkov decision processesreinforcement learningsample complexity

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites work

• A First-Order Approach to Accelerated Value Iteration
• An upper bound on the loss from approximate optimal-value functions
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model

This page was built for publication: Optimal approximation of average reward Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6986214)