PhD student, VUB
A Virtual Maze Game to Explain Reinforcement Learning
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 visualizes 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.
Youri Coppens pursues his PhD at the Vrije Universiteit Brussel. His research focuses on Explainable Reinforcement Learning and linking these to affective signals.
After obtaining his Msc degree, he spent a year in Japan doing an internship at Fujitsu Laboratories Ltd. on hardware acceleration for Deep Reinforcement Learning and wrote his first publication, which won a best paper award.