Identifying and exploiting features for effective plan retrieval in case-based planning

Mauro Vallati, Ivan Serina, Alessandro Saetti, Alfonso E. Gerevini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Case-Based planning can fruitfully exploit knowledge gained by solving a large number of problems, storing the corresponding solutions in a plan library and reusing them for solving similar planning problems in the future. Case-based planning is extremely effective when similar reuse candidates can be efficiently chosen. In this paper, we study an innovative technique based on planning problem features for efficiently retrieving solved planning problems (and relative plans) from large plan libraries. Since existing planning features are not always able to effectively distinguish between problems within the same planning domain, we introduce a new class of features. Our experimental analysis shows that the proposed features-based retrieval approach can significantly improve the performance of a state-of-theart case-based planning system.

Original languageEnglish
Title of host publicationProceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015)
EditorsRonen Brafman, Carmel Domshlak, Patrik Haslum, Shlomo Zilberstein
PublisherAAAI press
Pages239-243
Number of pages5
ISBN (Electronic)9781577357315
Publication statusPublished - Apr 2015
Event25th International Conference on Automated Planning and Scheduling - Jerusalem, Israel
Duration: 7 Jun 201511 Jun 2015
Conference number: 25
http://icaps15.icaps-conference.org (Link to Conference Website )

Conference

Conference25th International Conference on Automated Planning and Scheduling
Abbreviated titleICAPS 2015
CountryIsrael
CityJerusalem
Period7/06/1511/06/15
Internet address

Fingerprint

Planning

Cite this

Vallati, M., Serina, I., Saetti, A., & Gerevini, A. E. (2015). Identifying and exploiting features for effective plan retrieval in case-based planning. In R. Brafman, C. Domshlak, P. Haslum, & S. Zilberstein (Eds.), Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015) (pp. 239-243). AAAI press.
Vallati, Mauro ; Serina, Ivan ; Saetti, Alessandro ; Gerevini, Alfonso E. / Identifying and exploiting features for effective plan retrieval in case-based planning. Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015). editor / Ronen Brafman ; Carmel Domshlak ; Patrik Haslum ; Shlomo Zilberstein. AAAI press, 2015. pp. 239-243
@inproceedings{3472c9d3d5b3423c867a1172c544f37b,
title = "Identifying and exploiting features for effective plan retrieval in case-based planning",
abstract = "Case-Based planning can fruitfully exploit knowledge gained by solving a large number of problems, storing the corresponding solutions in a plan library and reusing them for solving similar planning problems in the future. Case-based planning is extremely effective when similar reuse candidates can be efficiently chosen. In this paper, we study an innovative technique based on planning problem features for efficiently retrieving solved planning problems (and relative plans) from large plan libraries. Since existing planning features are not always able to effectively distinguish between problems within the same planning domain, we introduce a new class of features. Our experimental analysis shows that the proposed features-based retrieval approach can significantly improve the performance of a state-of-theart case-based planning system.",
keywords = "case-based planning, planning features, plan retrieval",
author = "Mauro Vallati and Ivan Serina and Alessandro Saetti and Gerevini, {Alfonso E.}",
year = "2015",
month = "4",
language = "English",
pages = "239--243",
editor = "Ronen Brafman and Carmel Domshlak and Patrik Haslum and Shlomo Zilberstein",
booktitle = "Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015)",
publisher = "AAAI press",

}

Vallati, M, Serina, I, Saetti, A & Gerevini, AE 2015, Identifying and exploiting features for effective plan retrieval in case-based planning. in R Brafman, C Domshlak, P Haslum & S Zilberstein (eds), Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015). AAAI press, pp. 239-243, 25th International Conference on Automated Planning and Scheduling, Jerusalem, Israel, 7/06/15.

Identifying and exploiting features for effective plan retrieval in case-based planning. / Vallati, Mauro; Serina, Ivan; Saetti, Alessandro; Gerevini, Alfonso E.

Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015). ed. / Ronen Brafman; Carmel Domshlak; Patrik Haslum; Shlomo Zilberstein. AAAI press, 2015. p. 239-243.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Identifying and exploiting features for effective plan retrieval in case-based planning

AU - Vallati, Mauro

AU - Serina, Ivan

AU - Saetti, Alessandro

AU - Gerevini, Alfonso E.

PY - 2015/4

Y1 - 2015/4

N2 - Case-Based planning can fruitfully exploit knowledge gained by solving a large number of problems, storing the corresponding solutions in a plan library and reusing them for solving similar planning problems in the future. Case-based planning is extremely effective when similar reuse candidates can be efficiently chosen. In this paper, we study an innovative technique based on planning problem features for efficiently retrieving solved planning problems (and relative plans) from large plan libraries. Since existing planning features are not always able to effectively distinguish between problems within the same planning domain, we introduce a new class of features. Our experimental analysis shows that the proposed features-based retrieval approach can significantly improve the performance of a state-of-theart case-based planning system.

AB - Case-Based planning can fruitfully exploit knowledge gained by solving a large number of problems, storing the corresponding solutions in a plan library and reusing them for solving similar planning problems in the future. Case-based planning is extremely effective when similar reuse candidates can be efficiently chosen. In this paper, we study an innovative technique based on planning problem features for efficiently retrieving solved planning problems (and relative plans) from large plan libraries. Since existing planning features are not always able to effectively distinguish between problems within the same planning domain, we introduce a new class of features. Our experimental analysis shows that the proposed features-based retrieval approach can significantly improve the performance of a state-of-theart case-based planning system.

KW - case-based planning

KW - planning features

KW - plan retrieval

UR - http://www.scopus.com/inward/record.url?scp=84943254794&partnerID=8YFLogxK

UR - https://aaai.org/Press/Proceedings/icaps15.php

M3 - Conference contribution

SP - 239

EP - 243

BT - Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015)

A2 - Brafman, Ronen

A2 - Domshlak, Carmel

A2 - Haslum, Patrik

A2 - Zilberstein, Shlomo

PB - AAAI press

ER -

Vallati M, Serina I, Saetti A, Gerevini AE. Identifying and exploiting features for effective plan retrieval in case-based planning. In Brafman R, Domshlak C, Haslum P, Zilberstein S, editors, Proceedings of the 25th International Conference on Automated Planning and Scheduling (ICAPS 2015). AAAI press. 2015. p. 239-243