Reinforcement learning based local search for grouping problems: A case study on graph coloring

作者：

Highlights：

• Grouping problems naturally arise in numerous domains.

• This paper proposes a reinforcement learning based local search approach for grouping problems.

• The proposed approach is applied to the well-known graph coloring problem.

• Computational results are presented on a set of benchmark instances.

摘要

•Grouping problems naturally arise in numerous domains.•This paper proposes a reinforcement learning based local search approach for grouping problems.•The proposed approach is applied to the well-known graph coloring problem.•Computational results are presented on a set of benchmark instances.

论文关键词：Grouping problems,Reinforcement learning,Heuristics,Learning-based optimization

论文评审过程：Received 6 February 2016, Revised 25 June 2016, Accepted 10 July 2016, Available online 4 August 2016, Version of Record 8 August 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.047