提出新型搜索框架，让学习与规划更好结合，提升求解效率。
Leveraging Action Relational Structures for Integrated Learning and Planning
- 设计部分空间搜索，利用动作关系结构细化搜索过程
- 新方法在IPC 2023学习赛道上超越当前最优模型
- 适合研究智能规划与机器学习融合的学者参考
近期规划研究尝试用学习方法辅助规划，但对搜索算法如何适配学习系统关注不足。本文提出部分空间搜索，一种基于PDDL动作模式中动作关系结构的新搜索空间，该结构被传统方法忽略。相比状态空间搜索，部分空间搜索提供更细粒度的视角，可更早剪枝劣质动作。为此引入动作集启发式，用于评估状态中的动作集合，并描述如何自动将现有启发式转换为动作集形式。同时，利用部分空间搜索生成的大规模训练数据，从零训练动作集启发式。新规划器LazyLifted整合了更优的搜索与学习启发式，在IPC 2023学习赛道（LT）基准上表现优于当前最先进方法。此外，其在高分支因子任务中也表现出高效性，在合并的IPC 2023 LT与高分支因子基准测试中超越LAMA。
原文摘要 · Abstract (English)
Recent advances in planning have explored using learning methods to help planning. However, little attention has been given to adapting search algorithms to work better with learning systems. In this paper, we introduce partial-space search, a new search space for classical planning that leverages the relational structure of actions given by PDDL action schemas -- a structure overlooked by traditional planning approaches. Partial-space search provides a more granular view of the search space and allows earlier pruning of poor actions compared to state-space search. To guide partial-space search, we introduce action set heuristics that evaluate sets of actions in a state. We describe how to automatically convert existing heuristics into action set heuristics. We also train action set heuristics from scratch using large training datasets from partial-space search. Our new planner, LazyLifted, exploits our better integrated search and learning heuristics and outperforms the state-of-the-art ML-based heuristic on IPC 2023 learning track (LT) benchmarks. We also show the efficiency of LazyLifted on high-branching factor tasks and show that it surpasses LAMA in the combined IPC 2023 LT and high-branching factor benchmarks.
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。