Extracting bottlenecks for reinforcement learning agent by holonic concept clustering and attentional functions

作者：

Highlights：

• Attentional functions are introduced to extract bottlenecks indirectly.

• The results showed a considerable improvement in the precision of detection.

• It has better time complexity comparing to other methods.

• It needs fewer requirements for designer's help comparing to other methods.

摘要

•Attentional functions are introduced to extract bottlenecks indirectly.•The results showed a considerable improvement in the precision of detection.•It has better time complexity comparing to other methods.•It needs fewer requirements for designer's help comparing to other methods.

论文关键词：Reinforcement learning,Abstraction,Concept,Holonic/hierarchical clustering,Attention

论文评审过程：Received 22 January 2015, Revised 13 January 2016, Accepted 14 January 2016, Available online 1 February 2016, Version of Record 16 February 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.01.030