State Encodings for GNN-Based Lifted Planners

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384781" target="_blank" >RIV/68407700:21230/25:00384781 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1609/aaai.v39i25.34853" target="_blank" >https://doi.org/10.1609/aaai.v39i25.34853</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1609/aaai.v39i25.34853" target="_blank" >10.1609/aaai.v39i25.34853</a>

Jazyk výsledku

angličtina

Název v původním jazyce

State Encodings for GNN-Based Lifted Planners

Popis výsledku v původním jazyce

The application of graph neural networks (GNNs) to learn heuristic functions in classical planning is gaining traction. Despite the variety of methods proposed in the literature to encode classical planning tasks for GNNs, a comparative study evaluating their relative performances has been lacking. Moreover, some encodings have been assessed solely for their expressiveness rather than practical effectiveness in planning. This paper provides an extensive comparative analysis of existing encodings. Our results indicate that the smallest encoding based on Gaifman graphs, not yet applied in planning, outperforms the rest due to its fast evaluation times and the informativeness of the resulting heuristic. The overall coverage measured on the IPC almost reaches that of the state-of-the-art planner LAMA while exhibiting rather complementary strengths across different domains.

Název v anglickém jazyce

State Encodings for GNN-Based Lifted Planners

Popis výsledku anglicky

The application of graph neural networks (GNNs) to learn heuristic functions in classical planning is gaining traction. Despite the variety of methods proposed in the literature to encode classical planning tasks for GNNs, a comparative study evaluating their relative performances has been lacking. Moreover, some encodings have been assessed solely for their expressiveness rather than practical effectiveness in planning. This paper provides an extensive comparative analysis of existing encodings. Our results indicate that the smallest encoding based on Gaifman graphs, not yet applied in planning, outperforms the rest due to its fast evaluation times and the informativeness of the resulting heuristic. The overall coverage measured on the IPC almost reaches that of the state-of-the-art planner LAMA while exhibiting rather complementary strengths across different domains.

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

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 39th AAAI Conference on Artificial Intelligence

ISBN

978-1-57735-897-8

ISSN

2159-5399

e-ISSN

2374-3468

Počet stran výsledku

9

Strana od-do

26525-26533

Název nakladatele

AAAI Press

Místo vydání

Menlo Park

Místo konání akce

Philadelphia

Datum konání akce

27. 2. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001477487000037