EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

N -to-1 Knowledge Transfer in Reinforcement Learning via Adaptive Q -Function Selection

Marko Ruman, Tatiana V. Guy

IEEE Access · 2026 · 14 · 45964-45976

DOI: 10.1109/access.2026.3676711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Marko Ruman und 1 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon Europe Research and Innovation Program Project “Identity Attributes Matrix Initiative (IAMI)”, COST Action, Joint UTIA-PEF Laboratory TALISMAN.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper tackles multi-source ( $N$ -to-1) knowledge transfer in reinforcement learning (RL), where an agent must adaptively solve a new task by leveraging a library of pre-learned skills. We consider a setting where these skills are represented as multiple $Q$ -functions and corresponding environment models, without any explicit labels to guide the selection. To address this scenario, we introduce a theoretically grounded method that dynamically selects the most suitable $Q$ -function at each learning stage. Instead of relying on noisy, short-term signals, our approach makes a farsighted choice by simulating the long-term performance of each skill while simultaneously evaluating the trustworthiness of its underlying world model. This allows the agent to intelligently transition from relying on transferred knowledge to using its own newly acquired policy. The proposed method is evaluated in three scenarios: 1) selection among multiple $Q$ -functions to solve a fixed RL task, 2) adaptation in a dynamically changing environment, and 3) switching from a partially learned $Q$ -function to a newly learned one. In all cases, our method accelerates learning and demonstrates robust adaptation, confirming its effectiveness for scalable multi-source transfer in RL.

Förderung

  • European Union’s Horizon Europe Research and Innovation Program Project “Identity Attributes Matrix Initiative (IAMI)”
  • COST Action
  • Joint UTIA-PEF Laboratory TALISMAN

Zitieren

APA

Ruman, M., & Guy, T. V. (2026). N -to-1 Knowledge Transfer in Reinforcement Learning via Adaptive Q -Function Selection. IEEE Access, 14, 45964-45976. https://doi.org/10.1109/access.2026.3676711

Vancouver

Ruman M, Guy TV. N -to-1 Knowledge Transfer in Reinforcement Learning via Adaptive Q -Function Selection. IEEE Access. 2026;14:45964-45976. doi:10.1109/access.2026.3676711

BibTeX
@article{Ruman2026,
  author = {Ruman, Marko and Guy, Tatiana V.},
  title = {N -to-1 Knowledge Transfer in Reinforcement Learning via Adaptive Q -Function Selection},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {45964--45976},
  doi = {10.1109/access.2026.3676711}
}
Kostenlos starten →