A Data-Driven Approach for Gin Rummy Hand Evaluation

AAAI 2021 pp. 15647-15654

doi:10.1609/AAAI.V35I17.17843 /aaai/2021/truong2021aaai-data/

Abstract

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.

PDF AAAI Semantic Scholar

Cite

Text

Truong and Neller. "A Data-Driven Approach for Gin Rummy Hand Evaluation." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I17.17843

Markdown

[Truong and Neller. "A Data-Driven Approach for Gin Rummy Hand Evaluation." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/truong2021aaai-data/) doi:10.1609/AAAI.V35I17.17843

BibTeX

@inproceedings{truong2021aaai-data,
  title     = {{A Data-Driven Approach for Gin Rummy Hand Evaluation}},
  author    = {Truong, Sang T. and Neller, Todd W.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15647-15654},
  doi       = {10.1609/AAAI.V35I17.17843},
  url       = {https://mlanthology.org/aaai/2021/truong2021aaai-data/}
}