EUVIMEDEUVIMED entdecken
Crossref

Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction

Mohamed K. Abdel-Aziz, Mohammed S. Elbamby, Sumudu Samarakoon, Mehdi Bennis

IEEE Transactions on Communications · 2024-06 · 72 (6) · 3454-3462

DOI: 10.1109/tcomm.2024.3365520 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2024-06. Verfasst von Mohamed K. Abdel-Aziz und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: European Union through the projects 6G-INTENSE, CENTRIC, Research Council of Finland (former Academy of Finland) 6G Flagship Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cooperative multi-agent reinforcement learning (MARL) for navigation enables agents to cooperate to achieve their navigation goals. Using emergent communication, agents learn a communication protocol to coordinate and share information that is needed to achieve their navigation tasks. In emergent communication, symbols with no pre-specified usage rules are exchanged, in which the meaning and syntax emerge through training. Learning a navigation policy along with a communication protocol in a MARL environment is highly complex due to the huge state space to be explored. To cope with this complexity, this work proposes a novel neural network architecture, for jointly learning an adaptive state space abstraction and a communication protocol among agents participating in navigation tasks. The goal is to come up with an adaptive abstractor that significantly reduces the size of the state space to be explored, without degradation in the policy performance. Simulation results show that the proposed method reaches a better policy, in terms of achievable rewards, resulting in fewer training iterations compared to the case where raw states or fixed state abstraction are used. Moreover, it is shown that a communication protocol emerges during training which enables the agents to learn better policies within fewer training iterations.

Förderung

  • European Union through the projects 6G-INTENSE
  • CENTRIC
  • Research Council of Finland (former Academy of Finland) 6G Flagship Program

Zitieren

APA

Abdel-Aziz, M. K., Elbamby, M. S., Samarakoon, S., & Bennis, M. (2024). Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction. IEEE Transactions on Communications, 72(6), 3454-3462. https://doi.org/10.1109/tcomm.2024.3365520

Vancouver

Abdel-Aziz MK, Elbamby MS, Samarakoon S, Bennis M. Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction. IEEE Transactions on Communications. 2024;72(6):3454-3462. doi:10.1109/tcomm.2024.3365520

BibTeX
@article{AbdelAziz2024,
  author = {Abdel-Aziz, Mohamed K. and Elbamby, Mohammed S. and Samarakoon, Sumudu and Bennis, Mehdi},
  title = {Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction},
  journal = {IEEE Transactions on Communications},
  year = {2024},
  volume = {72},
  number = {6},
  pages = {3454--3462},
  doi = {10.1109/tcomm.2024.3365520}
}
Kostenlos starten →