20.500.12556/RUP-21533 Qualitative control learning can be much faster than reinforcement learning Reinforcement learning has emerged as a prominent method for controlling dynamic systems in the absence of a precise mathematical model. However, its reliance on extensive interactions with the environment often leads to prolonged training periods. In this paper, we propose an alternative approach to learning control policies that focuses on learning qualitative models and uses symbolic planning to derive a qualitative plan for the control task, which is executed by an adaptive reactive controller. We conduct experiments utilizing our approach on the cart-pole problem, a standard benchmark in dynamic system control. We additionally extend this problem domain to include uneven terrains, such as driving over craters or hills, to assess the robustness of learned controllers. Our results indicate that qualitative learning offers significant advantages over reinforcement learning in terms of sample efficiency, transferability, and interpretability. We demonstrate that our proposed approach is at least two orders of magnitude more sample efficient in the cart-pole domain than the usual variants of reinforcement learning. qualitative modeling qualitative reasoning qualitative control transfer learning kvalitativno modeliranje kvalitativno sklepanje kvalitativno vodenje prenosno učenje true false false Angleški jezik Slovenski jezik Članek v reviji 2025-08-07 11:06:54 2025-08-07 11:06:55 2025-08-08 03:03:36 0000-00-00 00:00:00 2025 0 0 str. 1-21 article no. ǂ4 Vol. 114 2025 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 2025-01-14 004.85 0885-6125 10.1007/s10994-024-06724-7 222246659 RAZ_Soberl_Domen_2025.pdf RAZ_Soberl_Domen_2025.pdf 1 0481ED74AFC01EA22EAC32A81FB7E6DA c0109317b6d662257b2caa2fd47d17fd0f8e6aaa7dbeda73e12f90d9f4084cdd 07095a9e-736e-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31316 https://link.springer.com/article/10.1007/s10994-024-06724-7 1 e3300fca-736d-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31315 Fakulteta za matematiko, naravoslovje in informacijske tehnologije 0 0 0