Improving Search with Supervised Learning in Trick-Based Card Games
This work addresses a bottleneck in AI for trick-taking card games, offering a domain-specific improvement that is incremental over existing methods.
The paper tackled the problem of improving move value estimates in trick-taking card games by enhancing the sampling distribution, rather than just evaluation algorithms, and achieved a substantial increase in cardplay strength in Skat using a deep neural network trained on human gameplay data.
In trick-taking card games, a two-step process of state sampling and evaluation is widely used to approximate move values. While the evaluation component is vital, the accuracy of move value estimates is also fundamentally linked to how well the sampling distribution corresponds the true distribution. Despite this, recent work in trick-taking card game AI has mainly focused on improving evaluation algorithms with limited work on improving sampling. In this paper, we focus on the effect of sampling on the strength of a player and propose a novel method of sampling more realistic states given move history. In particular, we use predictions about locations of individual cards made by a deep neural network --- trained on data from human gameplay - in order to sample likely worlds for evaluation. This technique, used in conjunction with Perfect Information Monte Carlo (PIMC) search, provides a substantial increase in cardplay strength in the popular trick-taking card game of Skat.