Saved in:
Bibliographic Details
Main Authors: Chen, Dillon Z., Horčík, Rostislav, Šír, Gustav
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916431941074944
author Chen, Dillon Z.
Horčík, Rostislav
Šír, Gustav
author_facet Chen, Dillon Z.
Horčík, Rostislav
Šír, Gustav
contents Automated planning is a form of declarative problem solving which has recently drawn attention from the machine learning (ML) community. ML has been applied to planning either as a way to test `reasoning capabilities' of architectures, or more pragmatically in an attempt to scale up solvers with learned domain knowledge. In practice, planning problems are easy to solve but hard to optimise. However, ML approaches still struggle to solve many problems that are often easy for both humans and classical planners. In this paper, we thus propose a new ML approach that allows users to specify background knowledge (BK) through Datalog rules to guide both the learning and planning processes in an integrated fashion. By incorporating BK, our approach bypasses the need to relearn how to solve problems from scratch and instead focuses the learning on plan quality optimisation. Experiments with BK demonstrate that our method successfully scales and learns to plan efficiently with high quality solutions from small training data generated in under 5 seconds.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07923
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Learning for Generalised Planning with Background Knowledge
Chen, Dillon Z.
Horčík, Rostislav
Šír, Gustav
Artificial Intelligence
Automated planning is a form of declarative problem solving which has recently drawn attention from the machine learning (ML) community. ML has been applied to planning either as a way to test `reasoning capabilities' of architectures, or more pragmatically in an attempt to scale up solvers with learned domain knowledge. In practice, planning problems are easy to solve but hard to optimise. However, ML approaches still struggle to solve many problems that are often easy for both humans and classical planners. In this paper, we thus propose a new ML approach that allows users to specify background knowledge (BK) through Datalog rules to guide both the learning and planning processes in an integrated fashion. By incorporating BK, our approach bypasses the need to relearn how to solve problems from scratch and instead focuses the learning on plan quality optimisation. Experiments with BK demonstrate that our method successfully scales and learns to plan efficiently with high quality solutions from small training data generated in under 5 seconds.
title Deep Learning for Generalised Planning with Background Knowledge
topic Artificial Intelligence
url https://arxiv.org/abs/2410.07923