arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03049cs.AI
收藏

通用视频游戏博弈中实时蒙特卡洛树搜索的增强方法

Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing

Maastricht University(马斯特里赫特大学)

Dennis J. N. J. Soemers, Chiara F. Sironi, Torsten Schuster, Mark H. M. Winands

AI总结:

本文针对通用视频游戏博弈中实时蒙特卡洛树搜索提出八种增强方法,单独应用多数可显著提升胜率,组合后使六十款游戏平均胜率从31.0%提升至48.4%,接近2015年GVG-AI竞赛顶尖水平。

摘要:

通用视频游戏博弈(GVGP)是人工智能的一个领域,智能体在其中游玩多种事先未知的实时视频游戏。这限制了领域特定启发式方法的使用。蒙特卡洛树搜索(MCTS)是一种不依赖领域特定知识的游戏博弈搜索技术。本文讨论了GVGP中MCTS的八种增强方法:渐进历史、N-Gram选择技术、树重用、广度优先树初始化、损失规避、基于新颖性的剪枝、基于知识的评估以及确定性游戏检测。其中一些方法在现有文献中已有记载,并在GVGP背景下进行了扩展或引入,还有一些是针对MCTS的新颖增强方法。实验表明,大多数增强方法在单独应用时都能在胜率上带来具有统计学显著性的提升。当这些方法组合使用时,与原始MCTS实现相比,它们在六十款不同游戏上的平均胜率从31.0%提高到48.4%,接近2015年GVG-AI竞赛最佳智能体的竞争水平。

英文摘要:

General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, Knowledge-Based Evaluations, and Deterministic Game Detection. Some of these are known from existing literature, and are either extended or introduced in the context of GVGP, and some are novel enhancements for MCTS. Most enhancements are shown to provide statistically significant increases in win percentages when applied individually. When combined, they increase the average win percentage over sixty different games from 31.0% to 48.4% in comparison to a vanilla MCTS implementation, approaching a level that is competitive with the best agents of the GVG-AI competition in 2015.

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。

↑