Value Iteration for Long-Run Average Reward in Markov Decision Processes.

Ashok, Pranav and Chatterjee, Krishnendu and Daca, Przemyslaw and Kretínský, Jan and Meggendorfer, Tobias (2017) Value Iteration for Long-Run Average Reward in Markov Decision Processes. In: CAV 2017 : Computer Aided Verification. Lecture Notes in Computer Science . Springer, Cham, pp. 201-221. ISBN 9783319633862

Full text not available from this repository.

Abstract

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI) is one of the simplest and most efficient algorithmic approaches to MDPs with other properties, such as reachability objectives. Unfortunately, a naive extension of VI does not work for MDPs with long-run average rewards, as there is no known stopping criterion. In this work our contributions are threefold. (1) We refute a conjecture related to stopping criteria for MDPs with long-run average rewards. (2) We present two practical algorithms for MDPs with long-run average rewards based on VI. First, we show that a combination of applying VI locally for each maximal end-component (MEC) and VI for reachability objectives can provide approximation guarantees. Second, extending the above approach with a simulation-guided on-demand variant of VI, we present an anytime algorithm that is able to deal with very large models. (3) Finally, we present experimental results showing that our methods significantly outperform the standard approaches on several benchmarks.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
213815
Deposited By:
Deposited On:
06 Feb 2024 16:15
Refereed?:
Yes
Published?:
Published
Last Modified:
16 Jul 2024 05:25