Generating and Exploiting Cost Predictions in Heuristic State-Space Planning

Francesco Percassi, Alfonso Emilio Gerevini, Enrico Scala, Ivan Serina, Mauro Vallati

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

This paper proposes and investigates a novel way of combining machine learning and heuristic search to improve domain independent planning. On the learning side, we use learning to predict the plan cost of a good solution for a given instance. On the planning side, we propose a bound-sensitive heuristic function that exploits such a prediction in a state-space planner. Our function combines the input prediction derived inductively) with some pieces of information gathered during search (derived deductively). As the prediction can sometimes be grossly inaccurate, the function also provides means to recognise when the provided information is actually misguiding the search. Our experimental analysis demonstrates the usefulness of the proposed approach in a standard heuristic best-first search schema.
Original languageEnglish
Title of host publicationProceedings of the Thirtieth International Conference on Automated Planning and Scheduling
Subtitle of host publication(ICAPS 2020)
EditorsJ. Christopher Beck, Olivier Buffet, Jörg Hoffmann, Erez Karpas, Shirin Sohrabi
PublisherAAAI press
Pages569-573
Number of pages5
Volume30
ISBN (Print)9781577358244
DOIs
Publication statusPublished - 29 May 2020
Event30th International Conference on Automated Planning and Scheduling - Online, France
Duration: 19 Oct 202030 Oct 2020
Conference number: 30
https://icaps20.icaps-conference.org/

Publication series

NameProceedings International Conference on Automated Planning and Scheduling, ICAPS
PublisherAAAI Press
Volume30
ISSN (Print)2334-0835
ISSN (Electronic)2334-0843

Conference

Conference30th International Conference on Automated Planning and Scheduling
Abbreviated titleICAPS 2020
Country/TerritoryFrance
Period19/10/2030/10/20
Internet address

Fingerprint

Dive into the research topics of 'Generating and Exploiting Cost Predictions in Heuristic State-Space Planning'. Together they form a unique fingerprint.

Cite this