用模仿麻将AI的方式，让黑箱模型变得可解释
Mxplainer: Explain and Learn Insights by Imitating Mahjong Agents
- 通过参数化搜索算法模拟麻将AI决策路径
- 对人类和AI对手预测准确率超90%，优于决策树方法
- 能给出策略洞察和具体每步解释，适合想学AI的玩家
人们需要内化AI代理的技能以提升自身能力。本文聚焦于麻将——一种涉及不完全信息、需在随机性和隐藏信息中做出长期有效决策的多人游戏。尽管已有多个出色的麻将AI代理达到职业人类玩家水平，但这些代理常被视为黑箱，难以提取有效洞见。本文提出Mxplainer，一种可转换为神经网络的参数化搜索算法，用于学习黑箱代理的参数。在人类与AI代理上的实验表明，Mxplainer在动作预测上分别达到超过92%和90%的前三名准确率，且其近似结果忠实可解释，显著优于决策树方法（34.8%）。该方法不仅能揭示代理的策略特征，还可提供可操作的逐步决策解释。
原文摘要 · Abstract (English)
People need to internalize the skills of AI agents to improve their own capabilities. Our paper focuses on Mahjong, a multiplayer game involving imperfect information and requiring effective long-term decision-making amidst randomness and hidden information. Through the efforts of AI researchers, several impressive Mahjong AI agents have already achieved performance levels comparable to those of professional human players; however, these agents are often treated as black boxes from which few insights can be gleaned. This paper introduces Mxplainer, a parameterized search algorithm that can be converted into an equivalent neural network to learn the parameters of black-box agents. Experiments on both human and AI agents demonstrate that Mxplainer achieves a top-three action prediction accuracy of over 92% and 90%, respectively, while providing faithful and interpretable approximations that outperform decision-tree methods (34.8% top-three accuracy). This enables Mxplainer to deliver both strategy-level insights into agent characteristics and actionable, step-by-step explanations for individual decisions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。