Semantically Layered Representation for Planning Problems and Its Usage for Heuristic Computation Using Cellular Simultaneous Recurrent Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00364355" target="_blank" >RIV/68407700:21230/23:00364355 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5220/0011691000003393" target="_blank" >https://doi.org/10.5220/0011691000003393</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0011691000003393" target="_blank" >10.5220/0011691000003393</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semantically Layered Representation for Planning Problems and Its Usage for Heuristic Computation Using Cellular Simultaneous Recurrent Neural Networks

Popis výsledku v původním jazyce

Learning heuristic functions for classical planning algorithms has been a great challenge in the past years. The biggest bottleneck of this technique is the choice of an appropriate description of the planning problem suitable for machine learning. Various approaches were recently suggested in the literature, namely grid-based, image-like, and graph-based. In this work, we extend the latest grid-based representation with layered architecture capturing the semantics of the related planning problem. Such an approach can be used as a domain-independent model for further heuristic learning. This representation keeps the advantages of the grid-structured input and provides further semantics about the problem we can learn from. Together with the representation, we also propose a new network architecture based on the Cellular Simultaneous Recurrent Networks (CSRN) that is capable of learning from such data and can be used instead of a heuristic function in the state-space search algorithms.

Název v anglickém jazyce

Semantically Layered Representation for Planning Problems and Its Usage for Heuristic Computation Using Cellular Simultaneous Recurrent Neural Networks

Popis výsledku anglicky

Learning heuristic functions for classical planning algorithms has been a great challenge in the past years. The biggest bottleneck of this technique is the choice of an appropriate description of the planning problem suitable for machine learning. Various approaches were recently suggested in the literature, namely grid-based, image-like, and graph-based. In this work, we extend the latest grid-based representation with layered architecture capturing the semantics of the related planning problem. Such an approach can be used as a domain-independent model for further heuristic learning. This representation keeps the advantages of the grid-structured input and provides further semantics about the problem we can learn from. Together with the representation, we also propose a new network architecture based on the Cellular Simultaneous Recurrent Networks (CSRN) that is capable of learning from such data and can be used instead of a heuristic function in the state-space search algorithms.

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 15th International Conference on Agents and Artificial Intelligence

ISBN

978-989-758-623-1

ISSN

2184-3589

e-ISSN

2184-433X

Počet stran výsledku

8

Strana od-do

493-500

Název nakladatele

SCITEPRESS – Science and Technology Publications, Lda

Místo vydání

Lisboa

Místo konání akce

Lisbon

Datum konání akce

22. 2. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—