Synthesizing interpretable strategies for solving puzzle games

Synthesizing interpretable strategies for solving puzzle games
复制标题

综合解决益智游戏的可解释策略

DOI:
10.1145/3102071.3102084
复制
发表时间:
2017
期刊:
Proceedings of the International Conference on the Foundations of Digital Games - FDG '17
影响因子:
--
通讯作者:
Popović, Zoran
Popović, Zoran
中科院分区:
--
文献类型:
--
作者:
Butler, Eric;Torlak, Emina;Popović, Zoran

文献摘要

参考文献

被引文献

相似文献

理解玩家如何与游戏互动是设计师面临的一个重要挑战。当玩以解决问题为中心的游戏时,比如像数独或Nonograms这样的逻辑谜题,人们会使用丰富的领域特定知识和策略结构,这些知识和策略在游戏规则描述中并不明显。本文探讨了面向玩家的知识和策略的自动发现,其目标是实现从难度估计到谜题生成再到游戏进程分析的各种应用。以流行的益智游戏Nonograms为目标领域,我们提出了一个新的系统来学习人类可解释的规则来解决这些谜题。该系统采用由SMT求解器驱动的程序合成作为主要的学习机制。学习到的规则用特定于领域的语言表示为条件-操作规则的程序。给定游戏机制和一组小的nonogram谜题训练集,我们的系统能够学习健全、简洁的规则,并将其推广到现实世界的大型谜题测试集。我们表明,无论是在覆盖范围还是质量方面,学习到的规则都优于从教程和指南中绘制的nonogram文档策略。
Understanding how players interact with games is an important challenge for designers. When playing games centered around problem solving, such as logic puzzles like Sudoku or Nonograms, people employ a rich structure of domain-specific knowledge and strategies that are not obvious from the description of a game's rules. This paper explores automatic discovery of player-oriented knowledge and strategies, with the goal of enabling applications ranging from difficulty estimation to puzzle generation to game progression analysis. Using the popular puzzle game Nonograms as our target domain, we present a new system for learning human-interpretable rules for solving these puzzles. The system uses program synthesis, powered by an SMT solver, as the primary learning mechanism. The learned rules are represented as programs in a domain-specific language for condition-action rules. Given game mechanics and a training set of small Nonograms puzzles, our system is able to learn sound, concise rules that generalize to a test set of large real-world puzzles. We show that the learned rules outperform documented strategies for Nonograms drawn from tutorials and guides, both in terms of coverage and quality.
人们如何学习
DOI: 10.1002/9781118736494.ch2
发表时间: 2016
期刊: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
影响因子: --
作者:
J. Merriënboer
通讯作者: J. Merriënboer
没有玩家的游戏指标:理解游戏工件的策略
DOI: 10.1609/aiide.v7i3.12479
发表时间: 2011
期刊: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
影响因子: --
作者:
M. Nelson
通讯作者: M. Nelson
评估具有限制性游戏的竞技游戏平衡
DOI: --
发表时间: 2012
期刊: Artificial Intelligence and Interactive Digital Entertainment Conference
影响因子: --
作者:
Alexander Jaffe;Alex Miller;Erik Andersen;Yun;A. Karlin;Zoran Popovic
通讯作者: Zoran Popovic
Ceptre:一种用于建模生成交互系统的语言
DOI: 10.1609/aiide.v11i1.12784
发表时间: 2021
期刊: Game Stud.
影响因子: --
作者:
Chris Martens
通讯作者: Chris Martens
EGGG:游戏生成的自动化编程
DOI: 10.1147/sj.393.0782
发表时间: 2000
期刊: IBM Syst. J.
影响因子: --
作者:
Jon Orwant
通讯作者: Jon Orwant