Determining representativeness of training plans: A case of macro-operators

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10389701" target="_blank" >RIV/00216208:11320/18:10389701 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/18:00329346

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICTAI.2018.00081" target="_blank" >http://dx.doi.org/10.1109/ICTAI.2018.00081</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICTAI.2018.00081" target="_blank" >10.1109/ICTAI.2018.00081</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Determining representativeness of training plans: A case of macro-operators

Popis výsledku v původním jazyce

Most learning for planning approaches rely on analysis of training plans. This is especially the case for one of the best-known learning approach: the generation of macro-operators (macros). These plans, usually generated from a very limited set of training tasks, must provide a ground to extract useful knowledge that can be fruitfully exploited by planning engines. In that, training tasks have to be representative of the larger class of planning tasks on which planning engines will then be run. A pivotal question is how such a set of training tasks can be selected. To address this question, here we introduce a notion of structural similarity of plans. We conjecture that if a class of planning tasks presents structurally similar plans, then a small subset of these tasks is representative enough to learn the same knowledge (macros) as could be learnt from a larger set of tasks of the same class. We have tested our conjecture by focusing on two state-of-the-art macro generation approaches. Our large empirical analysis considering seven state-of-the-art planners, and fourteen benchmark domains from the International Planning Competition, generally confirms our conjecture which can be exploited for selecting small-yet-informative training sets of tasks.

Název v anglickém jazyce

Determining representativeness of training plans: A case of macro-operators

Popis výsledku anglicky

Most learning for planning approaches rely on analysis of training plans. This is especially the case for one of the best-known learning approach: the generation of macro-operators (macros). These plans, usually generated from a very limited set of training tasks, must provide a ground to extract useful knowledge that can be fruitfully exploited by planning engines. In that, training tasks have to be representative of the larger class of planning tasks on which planning engines will then be run. A pivotal question is how such a set of training tasks can be selected. To address this question, here we introduce a notion of structural similarity of plans. We conjecture that if a class of planning tasks presents structurally similar plans, then a small subset of these tasks is representative enough to learn the same knowledge (macros) as could be learnt from a larger set of tasks of the same class. We have tested our conjecture by focusing on two state-of-the-art macro generation approaches. Our large empirical analysis considering seven state-of-the-art planners, and fourteen benchmark domains from the International Planning Competition, generally confirms our conjecture which can be exploited for selecting small-yet-informative training sets of tasks.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA18-07252S" target="_blank" >GA18-07252S: MoRePlan: Modelování a reformulace plánovacích problémů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Tools with Artificial Intelligence, ICTAI 2018

ISBN

978-1-5386-7449-9

ISSN

1082-3409

e-ISSN

neuvedeno

Počet stran výsledku

5

Strana od-do

488-492

Název nakladatele

IEEE

Místo vydání

NEW YORK, NY 10017 USA

Místo konání akce

Volos, Greece

Datum konání akce

5. 11. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000457750200071