A Data-Driven Approach for Gin Rummy Hand Evaluation

We develop a data-driven approach for hand strength evaluation in the game of Gin Rummy. Employing Convolutional Neural Networks, Monte Carlo simulation, and Bayesian reasoning, we compute both offensive and defensive scores of a game state. After only one training cycle, the model was able to make sophisticated and human-like decisions with a 55.4%±0.8% win rate (90% confidence level) against a Simple player.