Deep reinforcement learning applied to the k-server problem

作者：

Highlights：

• A novel algorithm for the k-server problem.

• The algorithm is less susceptible to the curse of dimensionality problem.

• A new perspective on intelligent transport systems.

摘要

•A novel algorithm for the k-server problem.•The algorithm is less susceptible to the curse of dimensionality problem.•A new perspective on intelligent transport systems.

论文关键词：Deep reinforcement learning,Online problem,The k-server problem,Combinatorial optimization,Competitive location

论文评审过程：Received 11 March 2019, Revised 22 May 2019, Accepted 6 June 2019, Available online 7 June 2019, Version of Record 14 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.015