This paper proposes Meta-SAGE, a novel approach for improving the scalability
of deep reinforcement learning models for combinatorial optimization (CO)
tasks. Our method adapts pre-trained models to larger-scale problems in test
time by suggesting two components: a scale meta-learner (SML) and scheduled
adaptation with guided exploration (SAGE). First, SML transforms the context
embedding for subsequent adaptation of SAGE based on scale information. Then,
SAGE adjusts the model parameters dedicated to the context embedding for a
specific instance. SAGE introduces locality bias, which encourages selecting
nearby locations to determine the next location. The locality bias gradually
decays as the model is adapted to the target instance. Results show that
Meta-SAGE outperforms previous adaptation methods and significantly improves
scalability in representative CO tasks. Our source code is available at
this https URL

本文提出了 Meta-SAGE，一种用于改善组合优化（CO）任务中深度强化学习模型的可伸缩性的新方法。 我们的方法通过建议两个组件：一个比例元学习器（SML）和指导探索的计划适应性（SAGE），将预训练模型适应到测试时间中的更大规模的问题，结果表明 Meta-SAGE 优于以前的适应方法，并且显着提高了具有代表性的 CO 任务的可伸缩性。