Opponent Hand Estimation in the Game of Gin Rummy

Authors

  • Peter E. Francis Gettysburg College
  • Hoang A. Just Gettysburg College
  • Todd W. Neller Gettysburg College

Keywords:

Gin Rummy, Games, Card Games, Imperfect Information Games, Machine Learning, Convolutional Neural Networks, Bayes Rule, Pattern Recognition, Permutations, Superpermutations

Abstract

In this article, we describe various approaches to opponent hand estimation in the card game Gin Rummy. We use an application of Bayes' rule, as well as both simple and convolutional neural networks, to recognize patterns in simulated game play and predict the opponent's hand. We also present a new minimal-sized construction for using arrays to pre-populate hand representation images. Finally, we define various metrics for evaluating estimations, and evaluate the strengths of our different estimations at different stages of the game.

Downloads

Published

2021-05-18

How to Cite

Francis, P. E., Just, H. A., & Neller, T. W. (2021). Opponent Hand Estimation in the Game of Gin Rummy. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15496-15502. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17824