Reinforcement learning versus evolutionary computation: a survey on hybrid algorithms

Madalina M. Drugan (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

39 Citations (Scopus)

Abstract

A variety of Reinforcement Learning (RL) techniques blends with one or more techniques from Evolutionary Computation (EC) resulting in hybrid methods classified according to their goal, new focus, and their component methodologies. We denote this class of hybrid algorithmic techniques as the evolutionary computation versus reinforcement learning (ECRL) paradigm. This overview considers the entire spectrum of algorithmic aspects and proposes a novel methodology that analyses the technical resemblances and differences in ECRL. Our design analyses the motivation for each ECRL paradigm, the underlying natural models, the sub-component algorithmic techniques, as well as the properties of their ensemble.

Original languageEnglish
Pages (from-to)228-246
Number of pages19
JournalSwarm and Evolutionary Computation
Volume44
DOIs
Publication statusPublished - 1 Feb 2019

Keywords

  • Evolutionary computation
  • Hybrid algorithms
  • Natural paradigms
  • Reinforcement learning
  • Survey

Fingerprint

Dive into the research topics of 'Reinforcement learning versus evolutionary computation: a survey on hybrid algorithms'. Together they form a unique fingerprint.

Cite this