Informace o publikaci

Verification of Markov Decision Processes using Learning Algorithms

Autoři

BRÁZDIL Tomáš CHATTERJEE Krishnendu CHMELÍK Martin FOREJT Vojtěch KŘETÍNSKÝ Jan KWIATKOWSKA Marta PARKER David UJMA Mateusz

Druh Článek ve sborníku
Konference Automated Technology for Verification and Analysis - 12th International Symposium, ATVA 2014
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
Doi http://dx.doi.org/10.1007/978-3-319-11936-6_8
Obor Informatika
Klíčová slova stochastic systems; verification; machine learning; statistical model checking; reinforcement learning
Popis 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 approaches, we do not restrict our attention to time-bounded (finite-horizon) or discounted properties, nor assume any particular properties of the MDP. We also show how our techniques extend to LTL objectives. We present experimental results showing the performance of our framework on several examples.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info