EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning

Seongmin Park, Hyungmin Kim, Hyunhak Kim, Jungwook Choi

IEEE Access · 2024 · 12 · 36055-36065

DOI: 10.1109/access.2024.3367002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Seongmin Park und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Korean government, A Study of Hyper-Connected Thinking Internet Technology by autonomous connecting, controlling, and evolving ways) and the research fund of Hanyang University, Development of Ultra-Low Power Deep Learning Processor Technology using Advanced Data Reuse for Edge Applications.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Korean government
  • A Study of Hyper-Connected Thinking Internet Technology by autonomous connecting, controlling, and evolving ways) and the research fund of Hanyang University
  • Development of Ultra-Low Power Deep Learning Processor Technology using Advanced Data Reuse for Edge Applications
  • Ministry of Science and ICT

Zitieren

APA

Park, S., Kim, H., Kim, H., & Choi, J. (2024). Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning. IEEE Access, 12, 36055-36065. https://doi.org/10.1109/access.2024.3367002

Vancouver

Park S, Kim H, Kim H, Choi J. Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning. IEEE Access. 2024;12:36055-36065. doi:10.1109/access.2024.3367002

BibTeX
@article{Park2024,
  author = {Park, Seongmin and Kim, Hyungmin and Kim, Hyunhak and Choi, Jungwook},
  title = {Pruning With Scaled Policy Constraints for Light-Weight Reinforcement Learning},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {36055--36065},
  doi = {10.1109/access.2024.3367002}
}
Kostenlos starten →