Computer Science Department
Students Develop AI to play Gin Rummy (Summer, 2020)
Drs. Steven Bogaerts and Chad Byers collaborated virtually on research with Masayuki Nagai, Kavya Shrivastava, and Kien Ta during summer 2020. They developed an artificial intelligence system to play the card game Gin Rummy. The system includes three main components to make decisions about drawing cards, discarding, and ending the game, with numerous parameters controlling behavior. The team applied an ensemble approach to the discard decision, and a series of parameter-tuning experiments to improve performance. This work culminated in a co-authored paper, “A Highly Parameterized Ensemble to Play Gin Rummy”. The paper was peer-reviewed and accepted for publication as part of the Educational Advances in Artificial Intelligence (EAAI) workshop at the 2021 conference of the Association for Advancement of Artificial Intelligence (AAAI). Masayuki, Kavya, and Kien will present the paper (virtually) at the conference in February 2021.
