Heuristic Learning in Domain-Independent Planning: Theoretical Analysis and Experimental Evaluation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10439480" target="_blank" >RIV/00216208:11320/21:10439480 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-71158-0_12" target="_blank" >https://doi.org/10.1007/978-3-030-71158-0_12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-71158-0_12" target="_blank" >10.1007/978-3-030-71158-0_12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Heuristic Learning in Domain-Independent Planning: Theoretical Analysis and Experimental Evaluation

Popis výsledku v původním jazyce

Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic which is used to estimate a distance from a state to a goal state. In this paper, we present a technique to automatically construct an efficient heuristic for a given domain. The proposed approach is based on training a deep neural network using a set of solved planning problems as training data. We use a novel way of extracting features for states developed specifically for planning applications. Our experiments show that the technique is competitive with state-of-the-art domain-independent heuristic. We also introduce a theoretical framework to formally analyze behaviour of learned heuristics. We state and prove several theorems that establish bounds on the worst-case performance of learned heuristics.

Název v anglickém jazyce

Heuristic Learning in Domain-Independent Planning: Theoretical Analysis and Experimental Evaluation

Popis výsledku anglicky

Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic which is used to estimate a distance from a state to a goal state. In this paper, we present a technique to automatically construct an efficient heuristic for a given domain. The proposed approach is based on training a deep neural network using a set of solved planning problems as training data. We use a novel way of extracting features for states developed specifically for planning applications. Our experiments show that the technique is competitive with state-of-the-art domain-independent heuristic. We also introduce a theoretical framework to formally analyze behaviour of learned heuristics. We state and prove several theorems that establish bounds on the worst-case performance of learned heuristics.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

AGENTS AND ARTIFICIAL INTELLIGENCE, ICAART 2020

ISBN

978-3-030-71158-0

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

26

Strana od-do

254-279

Název nakladatele

SPRINGER INTERNATIONAL PUBLISHING AG

Místo vydání

CHAM

Místo konání akce

Valletta

Datum konání akce

22. 2. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000722435000012