2048-like games for teaching reinforcement learning

Article type: Research Article

Authors: Guei, Hung^{; *} | Wei, Ting-Han^{; *} | Wu, I-Chen^{; **}

Affiliations: Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan

Correspondence: [**] Corresponding author. E-mail: [email protected].

Note: [*] Equal contribution.

Abstract: 2048-like games are a family of single-player stochastic puzzle games, which consist of sliding numbered-tiles that combine to form tiles with larger numbers. Notable examples of games in this family include Threes!, 2048, and 2584. 2048-like games are highly suitable for educational purposes due to their simplicity and popularity. Numerous machine learning methods have been proposed to play 2048-like games; the application of these techniques can help students gain first-hand experience in implementing machine learning algorithms. This paper proposes a guideline for using 2048-like games for teaching reinforcement learning and computer game algorithms, while also summarizing our experience of using 2584 and Threes! as pedagogical tools that were well received judging by student feedback in two graduate level courses.

Keywords: 2048, Threes!, computer science, reinforcement learning, pedagogy, education

DOI: 10.3233/ICG-200144

Journal: ICGA Journal, vol. 42, no. 1, pp. 14-37, 2020