EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bandit-Based Multi-Agent Source Seeking with Safety Guarantees

Zhibin Ji, Dingqi Zhu, Bin Du

Applied Mathematics and Statistics · 2024

DOI: 10.53941/ams.2024.100005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Mathematics and Statistics, 2024. Verfasst von Zhibin Ji und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we focus on a multi-agent source seeking problem where the safety of agents is characterized by a set of linear constraints. In particular, the safety constraints are also dependent on the unknown environment states, which makes the source seeking problem challenging to solve. To overcome such a challenge, we introduce a new notion of measurable path and then specify the reachability condition for all agents. A time-sequence of exploration is further introduced to help the agents to escape the stuck positions. To provide a performance guarantee for our source seeking algorithm, we perform the regret analysis and show a sub-linear cumulative regret. Finally, we evaluate the effectiveness of our SafeSearch algorithm through a set of simulations.

Zitieren

APA

Ji, Z., Zhu, D., & Du, B. (2024). Bandit-Based Multi-Agent Source Seeking with Safety Guarantees. Applied Mathematics and Statistics. https://doi.org/10.53941/ams.2024.100005

Vancouver

Ji Z, Zhu D, Du B. Bandit-Based Multi-Agent Source Seeking with Safety Guarantees. Applied Mathematics and Statistics. 2024. doi:10.53941/ams.2024.100005

BibTeX
@article{Ji2024,
  author = {Ji, Zhibin and Zhu, Dingqi and Du, Bin},
  title = {Bandit-Based Multi-Agent Source Seeking with Safety Guarantees},
  journal = {Applied Mathematics and Statistics},
  year = {2024},
  doi = {10.53941/ams.2024.100005}
}
Kostenlos starten →