Grid Representation in Neural Networks for Automated Planning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00358914" target="_blank" >RIV/68407700:21230/22:00358914 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5220/0010918500003116" target="_blank" >https://doi.org/10.5220/0010918500003116</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0010918500003116" target="_blank" >10.5220/0010918500003116</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Grid Representation in Neural Networks for Automated Planning

Popis výsledku v původním jazyce

Automated planning and machine learning create a powerful combination of tools which allows us to apply general problem solving techniques to problems that are not modeled using classical planning techniques. In real-world scenarios and complex domains, creating a standardized representation is often a bottleneck as it has to be modeled by a human. That often limits the usage of planning algorithms to real-world problems. The standardized representation is also not a suitable for neural network processing and often requires further transformation. In this work, we focus on presenting three different grid representations that are well suited to model a variety of classical planning problems which can be then processed by neural networks without further modifications. We also analyze classical planning benchmarks in order to find domains that correspond to our proposed representations. Furthermore, we also show that domains that are not explicitly defined on a grid can be represented on a grid with minor modifications that are domain specific. We discuss advantages and drawbacks of our proposed representations, provide examples for many planning benchmarks and also discuss the importance of data and its structure when training neural networks for planning.

Název v anglickém jazyce

Grid Representation in Neural Networks for Automated Planning

Popis výsledku anglicky

Automated planning and machine learning create a powerful combination of tools which allows us to apply general problem solving techniques to problems that are not modeled using classical planning techniques. In real-world scenarios and complex domains, creating a standardized representation is often a bottleneck as it has to be modeled by a human. That often limits the usage of planning algorithms to real-world problems. The standardized representation is also not a suitable for neural network processing and often requires further transformation. In this work, we focus on presenting three different grid representations that are well suited to model a variety of classical planning problems which can be then processed by neural networks without further modifications. We also analyze classical planning benchmarks in order to find domains that correspond to our proposed representations. Furthermore, we also show that domains that are not explicitly defined on a grid can be represented on a grid with minor modifications that are domain specific. We discuss advantages and drawbacks of our proposed representations, provide examples for many planning benchmarks and also discuss the importance of data and its structure when training neural networks for planning.

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

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

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 3

ISBN

978-989-758-547-0

ISSN

—

e-ISSN

2184-433X

Počet stran výsledku

10

Strana od-do

871-880

Název nakladatele

SciTePress - Science and Technology Publications

Místo vydání

Porto

Místo konání akce

Online Streaming

Datum konání akce

3. 3. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000774776400106