Multi-agent learning via gradient ascent activity-based credit assignment

We consider the situation in which cooperating agents learn to achieve a common goal based solely on a global return that results from all agents’ behavior. The method proposed is based on taking into account the agents’ activity, which can be any additional information to help solving multi-agent d...

Descripción completa

Detalles Bibliográficos
Autores principales: Sabri, Oussama, Lehéricy, Luc, Muzy, Alexandre
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10502029/
https://www.ncbi.nlm.nih.gov/pubmed/37709830
http://dx.doi.org/10.1038/s41598-023-42448-9
_version_ 1785106230169042944
author Sabri, Oussama
Lehéricy, Luc
Muzy, Alexandre
author_facet Sabri, Oussama
Lehéricy, Luc
Muzy, Alexandre
author_sort Sabri, Oussama
collection PubMed
description We consider the situation in which cooperating agents learn to achieve a common goal based solely on a global return that results from all agents’ behavior. The method proposed is based on taking into account the agents’ activity, which can be any additional information to help solving multi-agent decentralized learning problems. We propose a gradient ascent algorithm and assess its performance on synthetic data.
format Online
Article
Text
id pubmed-10502029
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-105020292023-09-16 Multi-agent learning via gradient ascent activity-based credit assignment Sabri, Oussama Lehéricy, Luc Muzy, Alexandre Sci Rep Article We consider the situation in which cooperating agents learn to achieve a common goal based solely on a global return that results from all agents’ behavior. The method proposed is based on taking into account the agents’ activity, which can be any additional information to help solving multi-agent decentralized learning problems. We propose a gradient ascent algorithm and assess its performance on synthetic data. Nature Publishing Group UK 2023-09-14 /pmc/articles/PMC10502029/ /pubmed/37709830 http://dx.doi.org/10.1038/s41598-023-42448-9 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Sabri, Oussama
Lehéricy, Luc
Muzy, Alexandre
Multi-agent learning via gradient ascent activity-based credit assignment
title Multi-agent learning via gradient ascent activity-based credit assignment
title_full Multi-agent learning via gradient ascent activity-based credit assignment
title_fullStr Multi-agent learning via gradient ascent activity-based credit assignment
title_full_unstemmed Multi-agent learning via gradient ascent activity-based credit assignment
title_short Multi-agent learning via gradient ascent activity-based credit assignment
title_sort multi-agent learning via gradient ascent activity-based credit assignment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10502029/
https://www.ncbi.nlm.nih.gov/pubmed/37709830
http://dx.doi.org/10.1038/s41598-023-42448-9
work_keys_str_mv AT sabrioussama multiagentlearningviagradientascentactivitybasedcreditassignment
AT lehericyluc multiagentlearningviagradientascentactivitybasedcreditassignment
AT muzyalexandre multiagentlearningviagradientascentactivitybasedcreditassignment

Ejemplares similares