20.500.12556/DKUM-97592 GIANT: General intelligent AgeNt trainer Intelligent agent training is an active research area in artificial intelligence, primarily driven by reinforcement learning methods that utilize neural networks as decision-making systems. To broaden this field of research, we present the General Intelligent AgeNt Trainer, a flexible, modular, and scalable platform for training intelligent agents. The current implementation integrates evolutionary algorithms, with a particular focus on genetic pro gramming and behavior trees as interpretable decision-making systems. The platform’s architecture is designed for extensibility, allowing integration of additional machine learning techniques, optimization strategies, and decision-making systems. Furthermore, the platform aims to establish a benchmark for evaluating and comparing machine learning algorithms in both single-agent and multi-agent environments. machine learning evolutionary algorithms genetic programming optimization games multi-agent systems evolucijski algoritmi strojno učenje optimizacija računalniške igre true false true Elsevier B.V. Angleški jezik Slovenski jezik https://www.sciencedirect.com/journal/softwarex Članek v reviji 2026-03-23 14:17:41 2026-03-23 14:17:44 2026-07-01 07:22:40 0000-00-00 00:00:00 2026 0 0 9 str. Vol. 34, [article no.] 102607 Jun. 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2025-11-12 2026-03-11 2026-03-18 004.8 272404483 10.1016/j.softx.2026.102607 2352-7110 1-s2.0-S2352711026001007-main.pdf 1-s2.0-S2352711026001007-main.pdf 1 7B4E2368E9C28DE2A250E43A8DE020A3 36d98d84975b09a57c465fd9a47e4f5eda233396dae78dec8540071db78bb7b6 e55347b3-26ba-11f1-ab09-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=204721 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0