LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments
Electronics · 25.06.2023 · 12 (13) · 2814
DOI: 10.3390/electronics12132814 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 25.06.2023. Verfasst von J. de Curtò und 5 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitat Politècnica de València: R&D, GOETHE-University Frankfurt am Main, DePP–Dezentrale Plannung von Platoons im Straßengüterverkehr mit Hilfe einer KI auf Basis einzelner LKW.
Abstract (Originalsprache)
In this paper, we introduce an innovative approach to handling the multi-armed bandit (MAB) problem in non-stationary environments, harnessing the predictive power of large language models (LLMs). With the realization that traditional bandit strategies, including epsilon-greedy and upper confidence bound (UCB), may struggle in the face of dynamic changes, we propose a strategy informed by LLMs that offers dynamic guidance on exploration versus exploitation, contingent on the current state of the bandits. We bring forward a new non-stationary bandit model with fluctuating reward distributions and illustrate how LLMs can be employed to guide the choice of bandit amid this variability. Experimental outcomes illustrate the potential of our LLM-informed strategy, demonstrating its adaptability to the fluctuating nature of the bandit problem, while maintaining competitive performance against conventional strategies. This study provides key insights into the capabilities of LLMs in enhancing decision-making processes in dynamic and uncertain scenarios.
Förderung
- Universitat Politècnica de València: R&D
- GOETHE-University Frankfurt am Main
- DePP–Dezentrale Plannung von Platoons im Straßengüterverkehr mit Hilfe einer KI auf Basis einzelner LKW
- Center for Data Science & AI
- xAIBiology
Zitieren
APA
Curtò, J. D., Zarzà, I. D., Roig, G., Cano, J. C., Manzoni, P., & Calafate, C. T. (2023). LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments. Electronics, 12(13), 2814. https://doi.org/10.3390/electronics12132814
Vancouver
Curtò JD, Zarzà ID, Roig G, Cano JC, Manzoni P, Calafate CT. LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments. Electronics. 2023;12(13):2814. doi:10.3390/electronics12132814
BibTeX
@article{Curt2023,
author = {Curtò, J. de and Zarzà, I. de and Roig, Gemma and Cano, Juan Carlos and Manzoni, Pietro and Calafate, Carlos T.},
title = {LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments},
journal = {Electronics},
year = {2023},
volume = {12},
number = {13},
pages = {2814},
doi = {10.3390/electronics12132814}
}
EUVIMED