English

Finding Safe Zones of policies Markov Decision Processes

Machine Learning 2023-10-10 v2 Artificial Intelligence Data Structures and Algorithms Machine Learning

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 22 approximation for both the escape probability and SafeZone size, using a polynomial size sample complexity.

Keywords

Cite

@article{arxiv.2202.11593,
  title  = {Finding Safe Zones of policies Markov Decision Processes},
  author = {Lee Cohen and Yishay Mansour and Michal Moshkovitz},
  journal= {arXiv preprint arXiv:2202.11593},
  year   = {2023}
}

Comments

NeurIPS 2023