PulseAugur
实时 13:40:29
English(EN) Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

新的规划方法达到最先进性能

研究人员开发了一种新的通用规划方法,显著提高了经典规划领域学习策略的效率和性能。该方法通过引入搜索树的整体编码来增强迭代宽度(IW)策略,使关系图神经网络(R-GNNs)能够一次性评估所有转换。此外,还提出了抽象IW(1)以通过新颖性检查中的关系抽象来提高可扩展性。在IPC 2023基准测试上的评估表明,该方法达到了最先进的性能,优于以前的方法和LAMA规划器。 AI

影响 在经典规划领域建立了新的最先进水平,可能加速通用人工智能规划能力的研究。

排序理由 该集群包含一篇详细介绍经典规划新方法及其基准测试结果的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的规划方法达到最先进性能

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Hector Geffner ·

    高效前瞻编码和抽象宽度用于经典规划中的通用策略学习

    Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

    Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea…