两篇新研究论文介绍了在AI规划和组合搜索中学习可接受启发式方法的创新方法。其中一篇论文提出了一个使用深度学习和图算法学习成本划分的框架，保证了启发式方法的可接受性。另一篇论文提出了一种训练神经网络启发式的方法，该方法使用低估算算子和事后校准，以确保它们不会高估成本，从而保持搜索算法中解的最优性。 AI
影响 这些方法可以显著提高AI搜索算法在复杂问题解决场景中的效率和最优性。
排序理由 两篇在arXiv上发表的学术论文，详细介绍了AI中学习可接受启发式方法的新方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2606.04597v1 Announce Type: new Abstract: Admissible heuristics are essential for optimal planning, yet learning them remains challenging due to the risk of overestimation. Cost partitioning combines multiple abstraction heuristics while preserving admissibility, but comput…
arXiv:2606.04860v1 Announce Type: cross Abstract: Finding optimal solution paths for combinatorial puzzles like the Rubik's Cube, sliding tile puzzles, and Lights Out remains a classical challenge in artificial intelligence. Heuristic search algorithms, such as A* , guarantee pat…
Finding optimal solution paths for combinatorial puzzles like the Rubik's Cube, sliding tile puzzles, and Lights Out remains a classical challenge in artificial intelligence. Heuristic search algorithms, such as A* , guarantee path optimality only when using an admissible heurist…
Admissible heuristics are essential for optimal planning, yet learning them remains challenging due to the risk of overestimation. Cost partitioning combines multiple abstraction heuristics while preserving admissibility, but computing optimal partitions online is expensive. We p…