David Parker
Senior Lecturer, University of Birmingham
[BCC+14] Tomás Brázdil, Krishnendu Chatterjee, Martin Chmelík, Vojtěch Forejt, Jan Křetínský, Marta Kwiatkowska, David Parker and Mateusz Ujma. Verification of Markov Decision Processes using Learning Algorithms. In Proc. 12th International Symposium on Automated Technology for Verification and Analysis (ATVA'14), volume 8837 of LNCS, pages 98-114, Springer. November 2014. [pdf] [bib] [Presents MDP verification techniques, implemented in PRISM, based on real-time dynamic programming and delayed Q-learning.]
Downloads:  pdf pdf (430 KB)  bib bib
Notes: A preliminary version of this paper is available at http://arxiv.org/abs/1402.2967. The original publication is available at www.springerlink.com.
Abstract. We present a general framework for applying machine-learning algorithms to the verification of Markov decision processes (MDPs). The primary goal of these techniques is to improve performance by avoiding an exhaustive exploration of the state space. Our framework focuses on probabilistic reachability, which is a core property for verification, and is illustrated through two distinct instantiations. The first assumes that full knowledge of the MDP is available, and performs a heuristic-driven partial exploration of the model, yielding precise lower and upper bounds on the required probability. The second tackles the case where we may only sample the MDP, and yields probabilistic guarantees, again in terms of both the lower and upper bounds, which provides efficient stopping criteria for the approximation. The latter is the first extension of statistical model checking for unbounded properties in MDPs. In contrast with other related techniques, our approach is not restricted to time-bounded (finite-horizon) or discounted properties, nor does it assume any particular properties of the MDP. We also show how our methods extend to LTL objectives. We present experimental results showing the performance of our framework on several examples.