A Virtual Maze Game to Explain Reinforcement Learning

Research output: Chapter in Book/Report/Conference proceedingConference paper


We demonstrate how Virtual Reality can explain the basic concepts of Reinforcement Learning through an interactive maze game. A player takes the role of an autonomous learning agent and must learn the shortest path to a hidden treasure through experience. This application visualises the learning process of Watkins' Q(λ), one of the fundamental algorithms in the field. A video can be found at https://youtu.be/sLJRiUBhQqM.
Original languageEnglish
Title of host publicationProceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019)
EditorsKatrien Beuls, Bart Bogaerts, Gianluca Bontempi, Pierre Geurts, Nick Harley, Bertrand Lebichot, Tom Lenaerts, Gilles Louppe, Paul Van Eecke
PublisherCEUR Workshop Proceedings
Number of pages2
ISBN (Electronic)1613-0073
Publication statusPublished - 8 Nov 2019
EventBNAIC 2019 - Brussels, Belgium
Duration: 7 Nov 20198 Nov 2019


ConferenceBNAIC 2019


  • Reinforcement Learning
  • Education
  • Virtual Reality

Fingerprint Dive into the research topics of 'A Virtual Maze Game to Explain Reinforcement Learning'. Together they form a unique fingerprint.

Cite this