arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.19463cs.AIcs.LG
收藏

优化规划启发式以进行排序,而非估计到达目标代价

Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal

Czech Technical University in Prague(布拉格捷克理工大学);Gen Digital, Inc.(Gen Digital 公司)

Leah Chrestien, Tomás Pevný, Stefan Edelkamp, Antonín Komenda

AI总结:

本文重新审视前向搜索算法中最优高效启发式的条件,提出基于排序的损失函数以替代估计到达目标代价,并通过实验验证了该理论的有效性。

摘要:

在规划的模仿学习中,启发式函数的参数针对一组已求解的问题实例进行优化。本文重新审视了前向搜索算法(主要是A*和贪心最佳优先搜索)严格最优高效启发式的必要与充分条件,这些算法仅扩展返回的最优路径上的状态。随后,本文提出了一族基于排序的损失函数,该损失函数针对给定的前向搜索算法变体量身定制。此外,从学习理论的角度,本文讨论了为何优化到达目标代价 \hstar\\ 是不必要地困难的。在多样化问题集上的实验比较明确地支持了所推导的理论。

英文摘要:

In imitation learning for planning, parameters of heuristic functions are optimized against a set of solved problem instances. This work revisits the necessary and sufficient conditions of strictly optimally efficient heuristics for forward search algorithms, mainly A* and greedy best-first search, which expand only states on the returned optimal path. It then proposes a family of loss functions based on ranking tailored for a given variant of the forward search algorithm. Furthermore, from a learning theory point of view, it discusses why optimizing cost-to-goal \hstar\ is unnecessarily difficult. The experimental comparison on a diverse set of problems unequivocally supports the derived theory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑