EUVIMEDEUVIMED entdecken
Crossref

Validation of social agent training: synthesis of reinforcement learning and evolutionary optimization methods

A. V. Chernikov

Informacionnye Tehnologii · 11.04.2026 · 32 (4) · 171-184

DOI: 10.17587/it.32.171-184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informacionnye Tehnologii, online erschienen am 11.04.2026. Verfasst von A. V. Chernikov. Die Arbeit nennt 46 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The article proposes a time series forecasting model designed for unstable and partially observable environments. Unlike traditional approaches, the developed FELAR architecture combines local agent learning with reward adjustment based on collective characteristics (trust, reputation, influence), alongside global evolutionary adaptation of strategies. The proposed model operates in a distributed multi-agent environment, enabling both local adaptive behavior and global strategy evolution. A set of experiments on publicly available time series datasets (urban traffic, transformer temperatures, electricity consumption) confirms the model’s high forecasting accuracy and robustness to concept drift. The article details the agent architecture, algorithmic loop, experimental setup, and computational efficiency of the approach. The paper highlights key advantages of the approach, including robustness to concept drift, real-time adaptability, and low computational overhead.

Zitieren

APA

Chernikov, A. V. (2026). Validation of social agent training: synthesis of reinforcement learning and evolutionary optimization methods. Informacionnye Tehnologii, 32(4), 171-184. https://doi.org/10.17587/it.32.171-184

Vancouver

Chernikov AV. Validation of social agent training: synthesis of reinforcement learning and evolutionary optimization methods. Informacionnye Tehnologii. 2026;32(4):171-184. doi:10.17587/it.32.171-184

BibTeX
@article{Chernikov2026,
  author = {Chernikov, A. V.},
  title = {Validation of social agent training: synthesis of reinforcement learning and evolutionary optimization methods},
  journal = {Informacionnye Tehnologii},
  year = {2026},
  volume = {32},
  number = {4},
  pages = {171--184},
  doi = {10.17587/it.32.171-184}
}
Kostenlos starten →