Analysis of Learning Heuristic Estimates for Grid Planning with Cellular Simultaneous Recurrent Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00372647" target="_blank" >RIV/68407700:21230/23:00372647 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s42979-023-02174-5" target="_blank" >https://doi.org/10.1007/s42979-023-02174-5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s42979-023-02174-5" target="_blank" >10.1007/s42979-023-02174-5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Analysis of Learning Heuristic Estimates for Grid Planning with Cellular Simultaneous Recurrent Networks

Popis výsledku v původním jazyce

Automated planning provides a powerful general problem solving tool, however, its need for a model creates a bottleneck that can be an obstacle to using automated planning algorithms in real-world settings. In this work, we propose to use cellular simultaneous recurrent networks (CSRN), to process a planning problem and provide a heuristic value estimate that can more efficiently steer the automated planning algorithms to a solution. Using this particular architecture provides us with a scale-free solution that can be used on any problem domain represented by a planar grid. We train the CSRN architecture on two benchmark domains and provide an analysis of its generalizing and scaling abilities. We also integrate the trained network into a planner and compare its performance against commonly used heuristic functions.

Název v anglickém jazyce

Analysis of Learning Heuristic Estimates for Grid Planning with Cellular Simultaneous Recurrent Networks

Popis výsledku anglicky

Automated planning provides a powerful general problem solving tool, however, its need for a model creates a bottleneck that can be an obstacle to using automated planning algorithms in real-world settings. In this work, we propose to use cellular simultaneous recurrent networks (CSRN), to process a planning problem and provide a heuristic value estimate that can more efficiently steer the automated planning algorithms to a solution. Using this particular architecture provides us with a scale-free solution that can be used on any problem domain represented by a planar grid. We train the CSRN architecture on two benchmark domains and provide an analysis of its generalizing and scaling abilities. We also integrate the trained network into a planner and compare its performance against commonly used heuristic functions.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

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

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

SN Computer Science

ISSN

2662-995X

e-ISSN

—

Svazek periodika

4

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

SG - Singapurská republika

Počet stran výsledku

22

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85173116731