涵盖无限状态空间的复杂序贯决策规划问题已被证明可通过AlphaZero类算法求解。这类在利用蒙特卡洛树搜索（Monte Carlo Tree Search，MCTS）算法模拟未来推演的同时训练神经模型的方法，已被证实可应用于现实规划问题。因此，与最终行为策略交互的工程师和用户，可从获取这些规划器离线或在线决策的自动化解释中获益。本文聚焦蒙特卡洛树搜索数据结构内的信息，就其构建方式而言，这些信息包含了序贯决策算法的大部分推理过程，对其可解释性至关重要。我们提出了利用信息论工具简化和约简蒙特卡洛树搜索并提取信息的新方法，这类信息可直接用于构建人类可理解的解释。我们证明，作为蒙特卡洛树搜索构建过程的集成部分，基础可解释性指标可在有限额外计算成本下计算得到。本文聚焦理论与算法层面，并提供了示例说明所提方法如何用于构建人类可理解的解释。
英文摘要：
Complex sequential decision-making planning problems, covering infinite states' space have been shown to be solvable by AlphaZero type of algorithms. Such an approach that trains a neural model while simulating projection of futures with a Monte Carlo Tree Search algorithm were shown to be applicable to real life planning problems. As such, engineers and users interacting with the resulting policy of behavior might benefit from obtaining automated explanations about these planners' decisions offline or online. This paper focuses on the information within the Monte Carlo Tree Search data structure. Given its construction, this information contains much of the reasoning of the sequential decision-making algorithm and is essential for its explainability. We show novel methods using information theoretic tools for the simplification and reduction of the Monte Carlo Tree Search and the extraction of information. Such information can be directly used for the construction of human understandable explanations. We show that basic explainability quantities can be calculated with limited additional computational cost, as an integrated part of the Monte Carlo Tree Search construction process. We focus on the theoretical and algorithmic aspects and provide examples of how the methods presented here can be used in the construction of human understandable explanations.
Arcane: An Assertion Reduction Framework through Semantic Clustering and MCTS-Guided Rule Exploring
State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China（处理器国家重点实验室，计算技术研究所，中国科学院，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics with Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis
xEEGNet: Towards Explainable AI in EEG Dementia Classification
Department of Neuroscience, University of Padua（帕多瓦大学神经科学系）；Padua Neuroscience Center（帕多瓦神经科学中心）；Department of Information Engineering, University of Padua（帕多瓦大学信息工程系）；Department of Physics and Astronomy, University of Padua（帕多瓦大学物理与天文学系）；Information Systems Institute, University of Applied Sciences Western Switzerland (HES-SO Valais)（瑞士西部应用科学大学信息系统研究所）
Intelligent Channel Allocation for IEEE 802.11be Multi-Link Operation: When MAB Meets LLM
School of Informatics, Xiamen University（厦门大学信息学院）；Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）
Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention
KAIST（韩国科学技术院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua University（清华大学）；Carnegie Mellon University（卡内基梅隆大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Washington（华盛顿大学）
XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models
King Fahd University of Petroleum and Minerals（国王法赫德石油和矿物大学）；Massachusetts Institute of Technology（麻省理工学院）；Imperial College London（伦敦帝国学院）；KFUPM-SDAIA Joint Research Centre for Artificial Intelligence（KFUPM-SDAIA联合人工智能研究中心）
An Explainable Machine Learning Framework for Railway Predictive Maintenance using Data Streams from the Metro Operator of Portugal
Information Technologies Group, atlanTTic, University of Vigo, Spain（信息科技组，atlanTTic，维戈大学，西班牙）；REMIT, Universidade Portucalense, Portugal（REMIT，葡萄牙普拉亚恩斯大学）；Faculty of Economics, University of Porto, Portugal（经济学院，波尔图大学，葡萄牙）；INESC TEC, Porto, Portugal（INESC TEC，波尔图，葡萄牙）；ISEP, Porto, Portugal（ISEP，波尔图，葡萄牙）
Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-making
The University of Manchester（曼彻斯特大学）；CRUK Manchester Institute（英国癌症研究中心曼彻斯特研究所）；Idiap Research Institute（Idiap研究所）
