arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.11902cs.AI
收藏

学习接地的一阶符号规划表示

Learning First-Order Symbolic Planning Representations That Are Grounded

Universitat Pompeu Fabra(庞培法布拉大学);Institució Catalana de Recerca i Estudis Avançats (ICREA)(加泰罗尼亚研究与高级研究院(ICREA));Linköping University(林雪平大学)

Andrés Occhipinti Liberman, Blai Bonet, Hector Geffner

摘要:

已经开发了两种主要方法来从非结构化数据中学习一阶规划(动作)模型:从状态空间的结构中产生清晰动作模式的组合方法,以及从图像表示的状态中产生动作模式的深度学习方法。前一种方法的一个好处是,学习到的动作图式类似于那些可以用手写的动作图式;后一种方法的一个好处是,学习到的表征(谓词)是基于图像的,因此,可以根据图像给出新的实例。在这项工作中,我们开发了一种新的公式,用于学习基于解析图像的清晰的一阶规划模型,这是结合两种方法的优点的一个步骤。解析图像被假定为在一个简单的O2 D语言(2D中的对象),涉及少量的一元和二进制谓词,如“左”,“上方”,“形状”等学习后,新的规划实例可以给出的解析图像对,一个用于初始情况,另一个用于目标。学习和规划实验报告的几个领域,包括块,推箱子,IPC网格和河内。

英文摘要:

Two main approaches have been developed for learning first-order planning (action) models from unstructured data: combinatorial approaches that yield crisp action schemas from the structure of the state space, and deep learning approaches that produce action schemas from states represented by images. A benefit of the former approach is that the learned action schemas are similar to those that can be written by hand; a benefit of the latter is that the learned representations (predicates) are grounded on the images, and as a result, new instances can be given in terms of images. In this work, we develop a new formulation for learning crisp first-order planning models that are grounded on parsed images, a step to combine the benefits of the two approaches. Parsed images are assumed to be given in a simple O2D language (objects in 2D) that involves a small number of unary and binary predicates like "left", "above", "shape", etc. After learning, new planning instances can be given in terms of pairs of parsed images, one for the initial situation and the other for the goal. Learning and planning experiments are reported for several domains including Blocks, Sokoban, IPC Grid, and Hanoi.

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。

↑