用图学习提升数值规划的效率与可解释性
Graph Learning for Numeric Planning
- 设计支持连续与分类属性的新型图核函数
- 在多个数据集上优于图神经网络，覆盖率达90%以上
- 适合需要可解释性与高效推理的规划任务
图学习天然适用于符号化、以对象为中心的规划，因其能利用规划领域中的关系结构，并处理任意数量对象的实例。数值规划是符号规划的扩展，状态中包含数值变量。本文提出高效且可解释的机器学习模型来解决数值规划任务，包括构建适用于具有连续与类别属性的图的新图核，以及用于学习数值规划启发式函数的新优化方法。实验表明，所提出的图核在效率和泛化能力上远超图神经网络，且与独立于领域的数值规划器相比，在覆盖率方面表现相当。代码已公开于 https://github.com/DillonZChen/goose。
原文摘要 · Abstract (English)
Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners. Code is available at https://github.com/DillonZChen/goose
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。