Random Forests for Opponent Hand Estimation in Gin Rummy

Anthony Hein, May Jiang, Vydhourie Thiyageswaran, Michael Guerzhoy

AAAI 2021 pp. 15545-15550

doi:10.1609/AAAI.V35I17.17830 /aaai/2021/hein2021aaai-random/

Abstract

We demonstrate an AI agent for the card game of Gin Rummy. The agent uses simple heuristics in conjunction with a model that predicts the probability of each card's being in the opponent's hand. To estimate the probabilities for cards' being in the opponent's hand, we generate a dataset of Gin Rummy games using self-play, and train a random forest on the game information states. We explore the random forest classifier we trained and study the correspondence between its outputs and intuitively correct outputs. Our agent wins 61% of games against a baseline heuristic agent that does not use opponent hand estimation.

PDF AAAI Semantic Scholar

Cite

Text

Hein et al. "Random Forests for Opponent Hand Estimation in Gin Rummy." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I17.17830

Markdown

[Hein et al. "Random Forests for Opponent Hand Estimation in Gin Rummy." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/hein2021aaai-random/) doi:10.1609/AAAI.V35I17.17830

BibTeX

@inproceedings{hein2021aaai-random,
  title     = {{Random Forests for Opponent Hand Estimation in Gin Rummy}},
  author    = {Hein, Anthony and Jiang, May and Thiyageswaran, Vydhourie and Guerzhoy, Michael},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15545-15550},
  doi       = {10.1609/AAAI.V35I17.17830},
  url       = {https://mlanthology.org/aaai/2021/hein2021aaai-random/}
}