Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling

Inguk Choi, Woo-Jin Shin, Sanghyun Cho, Hyun-Jung Kim

Keywords: Neural Combinatorial Optimization, Job Scheduling Problems, Multi-Policy Optimization

TL;DR: We introduce a novel multi-policy optimization framework with adaptive self-imitation learning for job scheduling problems.

Abstract: Reinforcement Learning (RL) has shown promising results in solving Job Scheduling Problems (JSPs), automatically deriving powerful dispatching rules from data without relying on expert knowledge. However, most RL-based methods train only a single decision-maker, which limits exploration capability and leaves significant room for performance improvement. Moreover, designing reward functions for different JSP variants remains a challenging and labor-intensive task. To address these limitations, we introduce a novel and generic learning framework that optimizes multiple policies sharing a common objective and a single neural network, while enabling each policy to learn specialized and diverse strategies. The model optimization process is fully guided in a self-supervised manner, eliminating the need for reward functions. In addition, we develop a training scheme that adaptively controls the imitation intensity to reflect the quality of self-labels. Experimental results show that our method effectively addresses the aforementioned challenges and significantly outperforms state-of-the-art RL methods across six JSP variants. Furthermore, our approach also demonstrates strong performance on other combinatorial optimization problems, highlighting its versatility beyond JSPs.

Primary Area: Optimization (e.g., convex and non-convex, stochastic, robust)

Submission Number: 9960