Deep Learning of Heuristics for Domain-independent Planning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424778" target="_blank" >RIV/00216208:11320/20:10424778 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5220/0008950400790088" target="_blank" >https://doi.org/10.5220/0008950400790088</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0008950400790088" target="_blank" >10.5220/0008950400790088</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning of Heuristics for Domain-independent Planning

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, where the heuristic (under)estimates 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 from the domain. We use a novel way of generating features for states which doesn&apos;t depend on usage of existing heuristics. The trained network can be used as a heuristic on any problem from the domain of interest without any limitation on the problem size. Our experiments show that the technique is competitive with popular domain-independent heuristic.

Název v anglickém jazyce

Deep Learning of Heuristics for Domain-independent Planning

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, where the heuristic (under)estimates 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 from the domain. We use a novel way of generating features for states which doesn&apos;t depend on usage of existing heuristics. The trained network can be used as a heuristic on any problem from the domain of interest without any limitation on the problem size. Our experiments show that the technique is competitive with popular domain-independent heuristic.

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

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICAART: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 2

ISBN

978-989-758-395-7

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

79-88

Název nakladatele

SCITEPRESS

Místo vydání

SETUBAL

Místo konání akce

Valletta

Datum konání akce

22. 2. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000570769000007