EUVIMEDEUVIMED entdecken
Crossref

Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach

Qiliang Chen, Babak Heydari

Journal of Mechanical Design · 29.05.2025 · 1-57

DOI: 10.1115/1.4068796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 29.05.2025. Verfasst von Qiliang Chen und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a framework that integrates variational autoencoders (VAE) with reinforcement learning (RL) to balance system performance and resource usage in multi-agent systems by dynamically adjusting network structures over time. A key innovation of this method is its capability to handle the vast action space of the network structure. This is achieved by combining Variational Auto-Encoder and Deep Reinforcement Learning to control the latent space encoded from the network structures. The proposed method, evaluated on the modified OpenAI particle environment under various scenarios, not only demonstrates superior performance compared to baselines but also reveals interesting strategies and insights through the learned behaviors.

Zitieren

APA

Chen, Q., & Heydari, B. (2025). Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach. Journal of Mechanical Design, 1-57. https://doi.org/10.1115/1.4068796

Vancouver

Chen Q, Heydari B. Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach. Journal of Mechanical Design. 2025:1-57. doi:10.1115/1.4068796

BibTeX
@article{Chen2025,
  author = {Chen, Qiliang and Heydari, Babak},
  title = {Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach},
  journal = {Journal of Mechanical Design},
  year = {2025},
  pages = {1--57},
  doi = {10.1115/1.4068796}
}
Kostenlos starten →