Cargando…
Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey
Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple a...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098527/ https://www.ncbi.nlm.nih.gov/pubmed/37050685 http://dx.doi.org/10.3390/s23073625 |
_version_ | 1785024831193874432 |
---|---|
author | Orr, James Dutta, Ayan |
author_facet | Orr, James Dutta, Ayan |
author_sort | Orr, James |
collection | PubMed |
description | Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning. |
format | Online Article Text |
id | pubmed-10098527 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100985272023-04-14 Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey Orr, James Dutta, Ayan Sensors (Basel) Review Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning. MDPI 2023-03-30 /pmc/articles/PMC10098527/ /pubmed/37050685 http://dx.doi.org/10.3390/s23073625 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Review Orr, James Dutta, Ayan Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title | Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title_full | Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title_fullStr | Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title_full_unstemmed | Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title_short | Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey |
title_sort | multi-agent deep reinforcement learning for multi-robot applications: a survey |
topic | Review |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098527/ https://www.ncbi.nlm.nih.gov/pubmed/37050685 http://dx.doi.org/10.3390/s23073625 |
work_keys_str_mv | AT orrjames multiagentdeepreinforcementlearningformultirobotapplicationsasurvey AT duttaayan multiagentdeepreinforcementlearningformultirobotapplicationsasurvey |