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.

翻译：通用视频游戏（GVGP）是人工智能的一个研究领域，其智能体需在预先未知的各类实时视频游戏中博弈。这一特性限制了领域特定启发式方法的应用。蒙特卡洛树搜索（MCTS）是一种不依赖领域知识的游戏博弈搜索技术。本文探讨了八种针对GVGP中MCTS的增强策略：渐进历史记录、N元选择技术、树结构复用、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。其中部分方法源自现有文献，并在GVGP背景下进行了扩展或引入，另一些则是MCTS的全新增强技术。实验表明，多数增强策略在单独应用时均能显著提升胜率。当组合使用时，相较于基础MCTS实现，这些方法在六十款不同游戏中的平均胜率从31.0%提升至48.4%，其表现已接近2015年GVG-AI竞赛中顶尖智能体的竞技水平。