Reinforcement Learning 101 with a Virtual Reality Game
 
Reinforcement Learning 101 with a Virtual Reality Game 
 
Youri Coppens, Eugenio Bargiacchi, Ann Nowe
 
Abstract 

Our proof-of-concept demonstrates how Virtual Reality can be used to explain the basic concepts of Reinforcement Learning. This application visualizes the learning process of Watkins' Q(λ), a fundamental algorithm in the field, in the form of an interactive treasure hunt game. A player takes the role of an autonomous agent, and must learn the shortest path to a hidden treasure through experience. The application also allows an audience to follow the game from an external display.