Graph Learning for Planning: The Story Thus Far and Open Challenges

TL;DR

This paper reviews the use of graph learning in planning, introduces the GOOSE framework for scaling learning from small to large tasks, and discusses five open challenges in the field.

Contribution

It provides a comprehensive analysis of graph learning applications in planning and proposes the GOOSE framework to enhance scalability and performance.

Findings

Graph representations improve planning performance.

Graph learning architectures impact learning efficiency.

The GOOSE framework enables scaling from small to large planning tasks.

Abstract

Graph learning is naturally well suited for use in planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. In this paper, we study the usage of graph learning for planning thus far by studying the theoretical and empirical effects on learning and planning performance of (1) graph representations of planning tasks, (2) graph learning architectures, and (3) optimisation formulations for learning. Our studies accumulate in the GOOSE framework which learns domain knowledge from small planning tasks in order to scale up to much larger planning tasks. In this paper, we also highlight and propose the 5 open challenges in the general Learning for Planning field that we believe need to be addressed for advancing the state-of-the-art.