A Game-centric Approach to Teaching Artificial Intelligence

• DOI: 10.5220/0007745203980404
• Publication Date: 2019-05-24T07:24:06Z
• Authors: Marc Pouly; Thomas Koller; Ruedi Arnold
• Keywords: 0303 health sciences; 03 medical and health sciences; 4. Education

Man vs. machine competitions have always been attracting much public attention and the famous defeats of human champions in chess, Jeopardy!, Go or poker undoubtedly mark important milestones history artificial intelligence. In this article we reflect on our experiences with a game-centric approach to teaching intelligence that follows historical development algorithms by popping hood these champion bots. Moreover, made available server infrastructure for playing card games perfect information imperfect mode, where students can evaluate their implementations increasingly sophisticated game-playing weekly online competitions, i.e. from rule-based systems exhaustive heuristic search game trees deep learning enhanced Monte Carlo methods reinforcement completely freed domain knowledge. The evaluation particular course setting revealed enthusiastic feedback not only but also university authority. What started as an experiment became part standard computer science curriculum after just one implementation.