Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systems

Giacomo Arcieri, Cyprien Hoelzl, Oliver Schwery, Daniel Straub, Konstantinos G. Papakonstantinou, Eleni N. Chatzi

Abstract: Highlights•A framework for POMDP inference and robust solution is proposed.•Transition and observation models are estimated via MCMC sampling.•Solutions merged with Bayesian decision making for robustness to model uncertainty.•A real-world problem of railway optimal maintenance with continuous data is solved.