@inproceedings{af124248f296468fb36222de4944c998,
title = "Finding Safe Zones of Markov Decision Processes Policies",
abstract = "Given a policy of a Markov Decision Process, we define a SAFEZONE as a subset of states, such that most of the policy's trajectories are confined to this subset. The quality of a SAFEZONE is parameterized by the number of states and the escape probability, i.e., the probability that a random trajectory will leave the subset. SAFEZONES are especially interesting when they have a small number of states and low escape probability. We study the complexity of finding optimal SAFEZONES, and show that in general, the problem is computationally hard. Our main result is a bi-criteria approximation learning algorithm with a factor of almost 2 approximation for both the escape probability and SAFEZONE size, using a polynomial size sample complexity.",
author = "Lee Cohen and Yishay Mansour and Michal Moshkovitz",
note = "Publisher Copyright: {\textcopyright} 2023 Neural information processing systems foundation. All rights reserved.; 37th Conference on Neural Information Processing Systems, NeurIPS 2023 ; Conference date: 10-12-2023 Through 16-12-2023",
year = "2023",
language = "الإنجليزيّة",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
editor = "A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine",
booktitle = "Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023",
address = "الولايات المتّحدة",
}