---
title: "Improving State Evaluation, Inference, and Search in Trick-Based Card Games"
authors:
  - "Michael Buro"
  - "Jeffrey Richard Long"
  - "Timothy Furtak"
  - "Nathan R. Sturtevant"
doi: ""
url: "https://ijcai.org/proceedings/2009/236"
pdf: "https://ijcai.org/proceedings/2009/0236.pdf"
venue: "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"
year: 2009
pages: "1407-1412"
track: ""
keywords:
---

# Improving State Evaluation, Inference, and Search in Trick-Based Card Games

Michael Buro, Jeffrey Richard Long, Timothy Furtak, Nathan R. Sturtevant

*Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence*, pages 1407-1412.

## Abstract

Skat is Germany's national card game played by millions of players around the world. In this paper, we present the world's first computer skat player that plays at the level of human experts. This performance is achieved by improving state evaluations using game data produced by human players and by using these state evaluations to perform inference on the unobserved hands of opposing players. Our results demonstrate the gains from adding inference to an imperfect information game player and show that training on data from average human players can result in expert-level playing strength.Michael Buro, Jeffrey Richard Long, Timothy Furtak, Nathan Sturtevant