Chapter

Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence

Volume 4682 of the series Lecture Notes in Computer Science pp 525-533

A Swarm-Based Learning Method Inspired by Social Insects

  • Xiaoxian HeAffiliated withShenyang Institute of Automation, Chinese Academy of Sciences, ShenyangGraduate school of the Chinese Academy of Sciences, Beijing
  • , Yunlong ZhuAffiliated withShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang
  • , Kunyuan HuAffiliated withShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang
  • , Ben NiuAffiliated withShenyang Institute of Automation, Chinese Academy of Sciences, ShenyangGraduate school of the Chinese Academy of Sciences, Beijing

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Inspired by cooperative transport behaviors of ants, on the basis of Q-learning, a new learning method, Neighbor-Information-Reference (NIR) learning method, is present in the paper. This is a swarm-based learning method, in which principles of swarm intelligence are strictly complied with. In NIR learning, the i-interval neighbor’s information, namely its discounted reward, is referenced when an individual selects the next state, so that it can make the best decision in a computable local neighborhood. In application, different policies of NIR learning are recommended by controlling the parameters according to time-relativity of concrete tasks. NIR learning can remarkably improve individual efficiency, and make swarm more “intelligent”.

Keywords

Neighbor-Information-Reference (NIR) learning i-interval neighbor discounted reward Q-learning swarm intelligence