1-2-3-Go! Policy Synthesis for Parameterized Markov Decision Processes via Decision-Tree Learning and Generalization

Autor:	Azeem, Muqsit, Chakraborty, Debraj, Kanav, Sudeep, Kretinsky, Jan, Mohagheghi, Mohammadsadegh, Mohr, Stefanie, Weininger, Maximilian
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Logic in Computer Science Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
Popis:	Despite the advances in probabilistic model checking, the scalability of the verification methods remains limited. In particular, the state space often becomes extremely large when instantiating parameterized Markov decision processes (MDPs) even with moderate values. Synthesizing policies for such \emph{huge} MDPs is beyond the reach of available tools. We propose a learning-based approach to obtain a reasonable policy for such huge MDPs. The idea is to generalize optimal policies obtained by model-checking small instances to larger ones using decision-tree learning. Consequently, our method bypasses the need for explicit state-space exploration of large models, providing a practical solution to the state-space explosion problem. We demonstrate the efficacy of our approach by performing extensive experimentation on the relevant models from the quantitative verification benchmark set. The experimental results indicate that our policies perform well, even when the size of the model is orders of magnitude beyond the reach of state-of-the-art analysis tools. Comment: Preprint. Under review
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.18293 Zobrazit plný text záznamu View this record from Arxiv