0640700 20260218131207.220251031235959.9 10.5281/zenodo.15854639 1 s. E cav_un_epca*064623932-32PragueCzech University of Life Sciences Prague2025GuyTatiana ValentinePelikánMartinKárnýMiroslavGajAleksejRužejnikovJurijRumanMarko Quantum Mechanics Imitation Learning Superposition Entanglement Intelligent Agents Decision-Making cav_un_auth*0355639 Fakhimi Derakhshan Siavash UTIA-B Adaptivní systémy Department of Adaptive Systems AS AS IR 100 Ústav teorie informace a automatizace AV ČR, v. v. i. https://zenodo.org/records/16900460 CA21169 EC cav_un_auth*0452289 In this study on imitation learning, the quantum logic of events has been utilized to reformulate data-driven decision-making processes for intelligent agents. By leveraging concepts such as superposition and entanglement, this approach enhances how agents learn from expert demonstrations. Key aspects of this method include the ability to evaluate multiple strategies simultaneously through superposition and to recognize interconnected decision-making patterns through entanglement. Additionally, this framework addresses uncertainty in data, considering probabilistic modelling as a vital component that tackles decision-making challenges in systems characterized by stochastic representations. While a completely new approach is not being proposed at this stage, this integration of quantum logic offers a solid foundation for potential future innovations in this field. This reformulation may facilitate a deeper exploration of strategies that could lead to valuable applications across various sectors, including robotics, autonomous systems, healthcare, and finance. As work continues, it is hoped that these foundational changes will contribute to advancements in the capabilities of intelligent agents operating under uncertainty and complexity. In this study on imitation learning, the quantum logic of events has been utilized to reformulate data-driven decision-making processes for intelligent agents. By leveraging concepts such as superposition and entanglement, this approach enhances how agents learn from expert demonstrations. Key aspects of this method include the ability to evaluate multiple strategies simultaneously through superposition and to recognize interconnected decision-making patterns through entanglement. Additionally, this framework addresses uncertainty in data, considering probabilistic modelling as a vital component that tackles decision-making challenges in systems characterized by stochastic representations. While a completely new approach is not being proposed at this stage, this integration of quantum logic offers a solid foundation for potential future innovations in this field. This reformulation may facilitate a deeper exploration of strategies that could lead to valuable applications across various sectors, including robotics, autonomous systems, healthcare, and finance. As work continues, it is hoped that these foundational changes will contribute to advancements in the capabilities of intelligent agents operating under uncertainty and complexity. cav_un_auth*0491465 DYNALIFE 2025 : Conference on QUANTUM INFORMATION AND DECISION MAKING IN LIFE SCIENCES 20250428 20250429 Prague CZ BB 10000 10100 10101 2026 1 PO https://hdl.handle.net/11104/0371110 cav_un_auth*0322033 Česká zemědělská univerzita v Praze, Provozně ekonomická fakulta PEF ČZU CZ S 2025 A2 SCOPUS PUBMED WOS DYNALIFE 2025 : Quantum Information and Decision Making in Life Sciences: Book of Abstracts Czech University of Life Sciences Prague 2025 Prague 32 32 cav_un_epca*0646239 Guy Tatiana Valentine 340 Pelikán Martin 340 Kárný Miroslav 340 Gaj Aleksej 340 Ružejnikov Jurij 340 Ruman Marko 340