Graph Learning for Numeric Planning.

Dillon Z. Chen; Sylvie Thiébaux

Graph Learning for Numeric Planning.

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

Abstract

Graph learning is naturally well suited for use in symbolic, object-centric planning
due to its ability to exploit relational structures exhibited in planning domains and
to take as input planning instances with arbitrary numbers of objects. Numeric
planning is an extension of symbolic planning in which states may now also exhibit
numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves
constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient
and generalise better than graph neural networks for numeric planning, and also
yield competitive coverage performance compared to domain-independent numeric
planners

Original language	English
Title of host publication	NeurIPS
Number of pages	28
Publication status	Published - 2024

Access to Document

Cite this

@inproceedings{7c0fcbf53648469e98f324ae9d78f814,

title = "Graph Learning for Numeric Planning.",

abstract = "Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners",

author = "Chen, \{Dillon Z.\} and Sylvie Thi{\'e}baux",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2024",

language = "English",

booktitle = "NeurIPS",

}

TY - GEN

T1 - Graph Learning for Numeric Planning.

AU - Chen, Dillon Z.

AU - Thiébaux, Sylvie

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2024

Y1 - 2024

N2 - Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners

AB - Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners

M3 - Conference Paper

BT - NeurIPS

ER -

Graph Learning for Numeric Planning.

Abstract

Access to Document

Fingerprint

Cite this