用图神经网络指导多智能体认知规划，提升求解效率。
Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics
- 用GNN学习认知状态的图结构特征，生成启发式评估
- 在多个实例上实现求解时间显著缩短，可处理更大规模问题
- 适合研究多智能体推理与规划的学者使用
多智能体认知规划（MEP）是一种用于推理物理世界和智能体信念的自主规划框架，在信息传递与认知一致性至关重要的领域具有应用价值。其状态需以克里普克结构（即有向带标签图）表示，这限制了现有启发式方法的适用性，导致求解器在无引导情况下探索指数级搜索空间，常陷入不可行。为此，本文利用图神经网络（GNN）挖掘认知状态中的模式与关系结构，从而对状态质量进行有意义估计——如距目标状态的距离，通过泛化先前求解实例的知识实现。将这些预测启发式集成至认知规划流程中，并与标准基线对比，实验表明该方法显著提升了多智能体认知规划的可扩展性。
原文摘要 · Abstract (English)
Multi-agent Epistemic Planning (MEP) is an autonomous planning framework for reasoning about both the physical world and the beliefs of agents, with applications in domains where information flow and awareness among agents are critical. The richness of MEP requires states to be represented as Kripke structures, i.e., directed labeled graphs. This representation limits the applicability of existing heuristics, hindering the scalability of epistemic solvers, which must explore an exponential search space without guidance, resulting often in intractability. To address this, we exploit Graph Neural Networks (GNNs) to learn patterns and relational structures within epistemic states, to guide the planning process. GNNs, which naturally capture the graph-like nature of Kripke models, allow us to derive meaningful estimates of state quality -- e.g., the distance from the nearest goal -- by generalizing knowledge obtained from previously solved planning instances. We integrate these predictive heuristics into an epistemic planning pipeline and evaluate them against standard baselines, showing improvements in the scalability of multi-agent epistemic planning.
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。