On the Power of Refined Skat Selection

TL;DR

This paper investigates strategies for selecting skat cards in the game of Skat, demonstrating how refined selection algorithms significantly improve AI performance in bidding and gameplay through expert rules and scoring functions.

Contribution

It introduces new refined skat evaluation features and selection strategies that enhance AI performance in Skat, especially in bidding and game selection phases.

Findings

Refined skat selection improves AI playing performance.

Expert rules and scoring functions enhance skat evaluation.

Skat selection strategies impact bidding success.

Abstract

Skat is a fascinating combinatorial card game, show-casing many of the intrinsic challenges for modern AI systems such as cooperative and adversarial behaviors (among the players), randomness (in the deal), and partial knowledge (due to hidden cards). Given the larger number of tricks and higher degree of uncertainty, reinforcement learning is less effective compared to classical board games like Chess and Go. As within the game of Bridge, in Skat we have a bidding and trick-taking stage. Prior to the trick-taking and as part of the bidding process, one phase in the game is to select two skat cards, whose quality may influence subsequent playing performance drastically. This paper looks into different skat selection strategies. Besides predicting the probability of winning and other hand strength functions we propose hard expert-rules and a scoring functions based on refined skat evaluation features. Experiments emphasize the impact of the refined skat putting algorithm on the playing performance of the bots, especially for AI bidding and AI game selection.