EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Design and Development of Multi-Agent Reinforcement Learning Intelligence on the Robotarium Platform for Embedded System Applications

Lorenzo Canese, Gian Carlo Cardarilli, Mohammad Mahdi Dehghan Pir, Luca Di Nunzio, Sergio Spanò

Electronics · 08.05.2024 · 13 (10) · 1819

DOI: 10.3390/electronics13101819 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 08.05.2024. Verfasst von Lorenzo Canese und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Project ECS 0000024 Rome Technopole, European Union—NextGenerationEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research explores the use of Q-Learning for real-time swarm (Q-RTS) multi-agent reinforcement learning (MARL) algorithm for robotic applications. This study investigates the efficacy of Q-RTS in the reducing convergence time to a satisfactory movement policy through the successful implementation of four and eight trained agents. Q-RTS has been shown to significantly reduce search time in terms of training iterations, from almost a million iterations with one agent to 650,000 iterations with four agents and 500,000 iterations with eight agents. The scalability of the algorithm was addressed by testing it on several agents’ configurations. A central focus was placed on the design of a sophisticated reward function, considering various postures of the agents and their critical role in optimizing the Q-learning algorithm. Additionally, this study delved into the robustness of trained agents, revealing their ability to adapt to dynamic environmental changes. The findings have broad implications for improving the efficiency and adaptability of robotic systems in various applications such as IoT and embedded systems. The algorithm was tested and implemented using the Georgia Tech Robotarium platform, showing its feasibility for the above-mentioned applications.

Förderung

  • Project ECS 0000024 Rome Technopole
  • European Union—NextGenerationEU

Zitieren

APA

Canese, L., Cardarilli, G. C., Pir, M. M. D., Nunzio, L. D., & Spanò, S. (2024). Design and Development of Multi-Agent Reinforcement Learning Intelligence on the Robotarium Platform for Embedded System Applications. Electronics, 13(10), 1819. https://doi.org/10.3390/electronics13101819

Vancouver

Canese L, Cardarilli GC, Pir MMD, Nunzio LD, Spanò S. Design and Development of Multi-Agent Reinforcement Learning Intelligence on the Robotarium Platform for Embedded System Applications. Electronics. 2024;13(10):1819. doi:10.3390/electronics13101819

BibTeX
@article{Canese2024,
  author = {Canese, Lorenzo and Cardarilli, Gian Carlo and Pir, Mohammad Mahdi Dehghan and Nunzio, Luca Di and Spanò, Sergio},
  title = {Design and Development of Multi-Agent Reinforcement Learning Intelligence on the Robotarium Platform for Embedded System Applications},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {10},
  pages = {1819},
  doi = {10.3390/electronics13101819}
}
Kostenlos starten →