A Reinforcement Learning Environment For Job-Shop Scheduling
This addresses the problem of efficient scheduling for automated systems like manufacturing, offering a competitive alternative to traditional methods, though it is incremental in improving DRL applications for combinatorial optimization.
The paper tackles the intractable job-shop scheduling problem by developing a deep reinforcement learning environment with a novel dense reward function, demonstrating that it significantly outperforms existing DRL methods and approaches state-of-the-art combinatorial optimization approaches on benchmark instances.
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.