Scheduling is a fundamental task occurring in various automated systems applications, e.g., optimal schedules for machines on a job shop allow for a reduction of production costs and waste. Nevertheless, finding such schedules is often intractable and cannot be achieved by Combinatorial Optimization Problem (COP) methods within a given time limit. Recent advances of Deep Reinforcement Learning (DRL) in learning complex behavior enable new COP application possibilities. This paper presents an efficient DRL environment for Job-Shop Scheduling -- an important problem in the field. Furthermore, we design a meaningful and compact state representation as well as a novel, simple dense reward function, closely related to the sparse make-span minimization criteria used by COP methods. We demonstrate that our approach significantly outperforms existing DRL methods on classic benchmark instances, coming close to state-of-the-art COP approaches.
@article{arxiv.2104.03760,
title = {A Reinforcement Learning Environment For Job-Shop Scheduling},
author = {Pierre Tassel and Martin Gebser and Konstantin Schekotihin},
journal= {arXiv preprint arXiv:2104.03760},
year = {2021}
}