145414 20250307094030.0 doi 10.3390/electronics12132814 sideral 140129 ART-2023-140129 eng Curtò, J. de LLM-Informed Multi-Armed Bandit Strategies for Non-Stationary Environments 2023 Access copy available to the general public Unrestricted 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. info:eu-repo/grantAgreement/ES/MCINN/AEI/PID2021-122580NB-I00 info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 2.6 2023 COMPUTER SCIENCE, INFORMATION SYSTEMS 115 / 250 = 0.46 2023 Q2 T2 PHYSICS, APPLIED 81 / 179 = 0.453 2023 Q2 T2 ENGINEERING, ELECTRICAL & ELECTRONIC 157 / 353 = 0.445 2023 Q2 T2 0.644 2023 Computer Networks and Communications 2023 Q2 Control and Systems Engineering 2023 Q2 Signal Processing 2023 Q2 Hardware and Architecture 2023 Q2 Electrical and Electronic Engineering 2023 Q2 5.3 2023 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Zarzà, I. de (orcid)0000-0002-5844-7871 Roig, Gemma Cano, Juan Carlos Manzoni, Pietro Calafate, Carlos T. 12, 13 (2023), 2814 [22 pp.] Electronics (Basel) Electronics 2079-9292 687410 http://zaguan.unizar.es/record/145414/files/texto_completo.pdf Versión publicada 2517150 http://zaguan.unizar.es/record/145414/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:145414 articulos driver 2025-03-07-09:38:56 ARTICLE