Policy-based primal-dual methods for concave CMDP with variance reduction

DOI10.1613/JAIR.1.18129MaRDI QIDQ6912804zbMATH OpenFDO

Authors Donghao Ying, Mengzi Amy Guo, Hyunin Lee, Javad Lavaei, Zuo-Jun (Max) Shen

Publication date 22 October 2025

Published in The Journal of Artificial Intelligence Research (JAIR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1613/JAIR.1.18129

zbMATH Keywords

machine learningMarkov decision processesprimal-dual methodreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Cites work

• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
• Achieving zero constraint violation for concave utility constrained reinforcement learning via primal-dual approach
• An actor-critic algorithm for constrained Markov decision processes
• Faster algorithm and sharper analysis for constrained Markov decision process
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• On the theory of policy gradient methods: optimality, approximation, and distribution shift
• Randomized linear programming solves the Markov decision problem in nearly linear (sometimes sublinear) time
• Risk-constrained reinforcement learning with percentile risk criteria
• Safety-aware apprenticeship learning

This page was built for publication: Policy-based primal-dual methods for concave CMDP with variance reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6912804)