Reinforcement learning driven heuristic for two-dimensional bandwidth minimization

Qing Zhou

doi:10.1016/j.asoc.2025.114327

Reinforcement learning driven heuristic for two-dimensional bandwidth minimization

2025-11-26

0

PRE

AI

DOI：10.1016/j.asoc.2025.114327

Original

Original request for help

Save

Abstract

En 中文

• An efficient reinforcement learning based algorithm is proposed for 2DBMP. • A tabu search method is used to explore a constrained neighborhood for exploitation. • The reported results are competitive compared to the existing best performing methods. • The design principle of combining learning and a metaheuristic approach is general. • The key essentials for the good performance of the algorithm are investigated.

Reinforcement learning driven heuristic for two-dimensional bandwidth minimization

Abstract

Journal

Organization