arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.09604cs.AI
收藏

用监督学习改进纸牌游戏中的搜索

Improving Search with Supervised Learning in Trick-Based Card Games

University of Alberta(阿尔伯塔大学)

Christopher Solinas, Douglas Rebstock, Michael Buro

摘要:

在纸牌游戏中,状态采样和评估的两步过程被广泛用于近似移动值。虽然评估组件至关重要,但移动值估计的准确性也从根本上与抽样分布与真实分布的对应程度有关。尽管如此,最近在纸牌游戏AI方面的工作主要集中在改进评估算法上,而在改进采样方面的工作有限。在本文中,我们专注于采样对球员的实力的影响,并提出了一种新的方法,采样更现实的状态移动历史。特别是,我们使用深度神经网络对单个卡片的位置进行预测-这种技术与完美信息蒙特卡罗(PIMC)搜索结合使用,在流行的Skat纸牌游戏中提供了纸牌游戏强度的大幅增加。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑