面向抽象与推理语料库的广义规划
Generalized Planning for the Abstraction and Reasoning Corpus
AI总结：
本文提出GPAR方法，将ARC抽象推理任务建模为带指针的广义规划问题，利用PDDL和领域知识约束提升求解性能，在以对象为中心的任务上超越现有最优求解器。
摘要：
抽象与推理语料库（ARC）是一个通用人工智能基准，由于其要求以推理和抽象为重点的流体智力，给纯机器学习方法带来了困难。在这项工作中，我们引入了一个ARC求解器，即面向抽象推理的广义规划（GPAR）。它将ARC问题转化为广义规划（GP）问题，其中解被形式化为带指针的规划程序。我们使用标准的规划域定义语言（PDDL）并结合表示以对象为中心的抽象的外部函数来表达每个ARC问题。我们展示了如何通过特定于ARC的领域知识来扩展GP求解器，这些知识以对动作模型、谓词、参数和规划程序有效结构的限制形式呈现。我们的实验表明，GPAR在ARC的以对象为中心的任务上优于最先进的求解器，证明了GP的有效性以及PDDL对ARC问题建模的表达能力。ARC基准带来的挑战激励着研究去推进现有GP求解器，并理解与其他规划计算模型的新关系。代码可在github.com/you68681/GPAR获取。
英文摘要：
The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that poses difficulties for pure machine learning methods due to its requirement for fluid intelligence with a focus on reasoning and abstraction. In this work, we introduce an ARC solver, Generalized Planning for Abstract Reasoning (GPAR). It casts an ARC problem as a generalized planning (GP) problem, where a solution is formalized as a planning program with pointers. We express each ARC problem using the standard Planning Domain Definition Language (PDDL) coupled with external functions representing object-centric abstractions. We show how to scale up GP solvers via domain knowledge specific to ARC in the form of restrictions over the actions model, predicates, arguments and valid structure of planning programs. Our experiments demonstrate that GPAR outperforms the state-of-the-art solvers on the object-centric tasks of the ARC, showing the effectiveness of GP and the expressiveness of PDDL to model ARC problems. The challenges provided by the ARC benchmark motivate research to advance existing GP solvers and understand new relations with other planning computational models. Code is available at github.com/you68681/GPAR.
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。
