An offline risk-aware policy selection method for Bayesian Markov decision processes

DOI10.1016/J.ARTINT.2026.104519MaRDI QIDQ7232471zbMATH OpenFDO

Authors Giorgio Angelotti, Nicolas Drougard, Caroline Ponzoni Carvalho Chanel

Publication date 23 April 2026

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.ARTINT.2026.104519

zbMATH Keywords

Bayesian Markov decision processoffline model learning for planningoffline policy selectionoffline reinforcement learningrisk-aware Markov decision process

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Coherent measures of risk
• Finite-time bounds for fitted value iteration
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• Planning with Markov decision processes. An AI perspective
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming

This page was built for publication: An offline risk-aware policy selection method for Bayesian Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7232471)