Outer-Learning Framework for Playing Multi-Player Trick-Taking Card Games: A Case Study in Skat

TL;DR

This paper introduces an outer-learning framework that enhances decision-making in multi-player trick-taking card games like Skat by combining human game data with self-play to improve predictions and support strategic choices.

Contribution

It presents a novel bootstrapping outer-learning framework that merges human and AI self-play data to improve early-game decision predictions in Skat.

Findings

Improved prediction accuracy through expanded game databases.

Self-improving engine with continuous knowledge refinement.

Effective support for various strategic decisions in Skat.

Abstract

In multi-player card games such as Skat or Bridge, the early stages of the game, such as bidding, game selection, and initial card selection, are often more critical to the success of the play than refined middle- and end-game play. At the current limits of computation, such early decision-making resorts to using statistical information derived from a large corpus of human expert games. In this paper, we derive and evaluate a general bootstrapping outer-learning framework that improves prediction accuracy by expanding the database of human games with millions of self-playing AI games to generate and merge statistics. We implement perfect feature hash functions to address compacted tables, producing a self-improving card game engine, where newly inferred knowledge is continuously improved during self-learning. The case study in Skat shows that the automated approach can be used to support various decisions in the game.