Publications
Publications › References ›
2024
Conference papers
Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet
[SBB+24]
Marnix Suilen, Thom Badings, Eline M. Bovy, David Parker and Nils Jansen.
Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet.
In Principles of Verification: Cycling the Probabilistic Landscape, volume 15262 of LNCS, pages 126–154, Springer.
November 2024.
pdf bib
[Surveys models and algorithms for robust verification under uncertainty, include those underlying PRISM's implementation.]
- Downloads
PDF 557 KB
BibTeX
- Notes
- The original publication is available at link.springer.com.
- Search for this paper
- Google · Google Scholar
Abstract
Markov decision processes (MDPs) are a standard model for sequential decision-making problems and are widely used across many scientific areas, including formal methods and artificial intelligence (AI). MDPs do, however, come with the restrictive assumption that the transition probabilities need to be precisely known. Robust MDPs (RMDPs) overcome this assumption by instead defining the transition probabilities to belong to some uncertainty set. We present a gentle survey on RMDPs, providing a tutorial covering their fundamentals. In particular, we discuss RMDP semantics and how to solve them by extending standard MDP methods such as value iteration and policy iteration. We also discuss how RMDPs relate to other models and how they are used in several contexts, including reinforcement learning and abstraction techniques. We conclude with some challenges for future work on RMDPs.