EUVIMEDEUVIMED entdecken
Crossref

QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning

Xiufeng Huang, Sheng Zhou

IEEE Transactions on Mobile Computing · 2024-05 · 23 (5) · 4739-4751

DOI: 10.1109/tmc.2023.3296726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-05. Verfasst von Xiufeng Huang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Natural Science Foundation of China, Hitachi Ltd..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the performance of multi-agent reinforcement learning under the constraint of wireless resources, we propose a message importance metric and design an importance-aware scheduling policy to effectively exchange messages. The key insight is spending the precious communication resources on important messages. The message importance depends not only on the messages themselves, but also on the needs of agents who receive them. Accordingly, we propose a query-message-based architecture, called QMNet. Agents generate queries and messages with the environment observation. Sharing queries can help calculate message importance. Exchanging messages can help agents cooperate better. Besides, we exploit the message importance to deal with random access collisions in decentralized systems. Furthermore, a message prediction mechanism is proposed to compensate for messages that are not transmitted. Finally, we evaluate the proposed schemes in a traffic junction environment, where only a fraction of agents can send messages due to limited wireless resources. Results show that QMNet can extract valuable information to guarantee the system performance even when only 30% of agents can share messages. By exploiting message prediction, the system can further save 40% of wireless resources. The importance-aware decentralized multi-access mechanism can effectively avoid collisions, achieving almost the same performance as centralized scheduling.

Förderung

  • Natural Science Foundation of China
  • Hitachi Ltd.

Zitieren

APA

Huang, X., & Zhou, S. (2024). QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning. IEEE Transactions on Mobile Computing, 23(5), 4739-4751. https://doi.org/10.1109/tmc.2023.3296726

Vancouver

Huang X, Zhou S. QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning. IEEE Transactions on Mobile Computing. 2024;23(5):4739-4751. doi:10.1109/tmc.2023.3296726

BibTeX
@article{Huang2024,
  author = {Huang, Xiufeng and Zhou, Sheng},
  title = {QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2024},
  volume = {23},
  number = {5},
  pages = {4739--4751},
  doi = {10.1109/tmc.2023.3296726}
}
Kostenlos starten →