English

Safe Learning for Near Optimal Scheduling

Artificial Intelligence 2021-07-14 v2 Logic in Computer Science

Abstract

In this paper, we investigate the combination of synthesis, model-based learning, and online sampling techniques to obtain safe and near-optimal schedulers for a preemptible task scheduling problem. Our algorithms can handle Markov decision processes (MDPs) that have 1020 states and beyond which cannot be handled with state-of-the art probabilistic model-checkers. We provide probably approximately correct (PAC) guarantees for learning the model. Additionally, we extend Monte-Carlo tree search with advice, computed using safety games or obtained using the earliest-deadline-first scheduler, to safely explore the learned model online. Finally, we implemented and compared our algorithms empirically against shielded deep Q-learning on large task systems.

Keywords

Cite

@article{arxiv.2005.09253,
  title  = {Safe Learning for Near Optimal Scheduling},
  author = {Damien Busatto-Gaston and Debraj Chakraborty and Shibashis Guha and Guillermo A. Pérez and Jean-François Raskin},
  journal= {arXiv preprint arXiv:2005.09253},
  year   = {2021}
}
R2 v1 2026-06-23T15:39:05.103Z