@article{MTMT:34762966,
	title = {Generally Applicable Q-Table Compression Method and Its Application for Constrained Stochastic Graph Traversal Optimization Problems},
	url = {https://m2.mtmt.hu/api/publication/34762966},
	author = {Kegyes, Tamás and Kummer, Alex and Süle, Zoltán and Abonyi, János},
	doi = {10.3390/info15040193},
	journal-iso = {INFORMATION-BASEL},
	journal = {INFORMATION (BASEL)},
	volume = {15},
	unique-id = {34762966},
	abstract = {We analyzed a special class of graph traversal problems, where the distances are stochastic, and the agent is restricted to take a limited range in one go. We showed that both constrained shortest Hamiltonian pathfinding problems and disassembly line balancing problems belong to the class of constrained shortest pathfinding problems, which can be represented as mixed-integer optimization problems. Reinforcement learning (RL) methods have proven their efficiency in multiple complex problems. However, researchers concluded that the learning time increases radically by growing the state- and action spaces. In continuous cases, approximation techniques are used, but these methods have several limitations in mixed-integer searching spaces. We present the Q-table compression method as a multistep method with dimension reduction, state fusion, and space compression techniques that project a mixed-integer optimization problem into a discrete one. The RL agent is then trained using an extended Q-value-based method to deliver a human-interpretable model for optimal action selection. Our approach was tested in selected constrained stochastic graph traversal use cases, and comparative results are shown to the simple grid-based discretization method.},
	year = {2024},
	eissn = {2078-2489},
	pages = {193},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Kummer, Alex/0000-0002-6550-5101; Süle, Zoltán/0000-0002-5589-2355; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:34728824,
	title = {Disassembly line optimization with reinforcement learning},
	url = {https://m2.mtmt.hu/api/publication/34728824},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	doi = {10.1007/s10100-024-00906-3},
	journal-iso = {CEJOR},
	journal = {CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH},
	volume = {2024},
	unique-id = {34728824},
	issn = {1435-246X},
	abstract = {As the environmental aspects become increasingly important, the disassembly problems have become the researcher’s focus. Multiple criteria do not enable finding a general optimization method for the topic, but some heuristics and classical formulations provide effective solutions. By highlighting that disassembly problems are not the straight inverses of assembly problems and the conditions are not standard, disassembly optimization solutions require human control and supervision. Considering that Reinforcement learning (RL) methods can successfully solve complex optimization problems, we developed an RL-based solution for a fully formalized disassembly problem. There were known successful implementations of RL-based optimizers. But we integrated a novel heuristic to target a dynamically pre-filtered action space for the RL agent ( dl O pt RL algorithm) and hence significantly raise the efficiency of the learning path. Our algorithm belongs to the Heuristically Accelerated Reinforcement Learning (HARL) method class. We demonstrated its applicability in two use cases, but our approach can also be easily adapted for other problem types. Our article gives a detailed overview of disassembly problems and their formulation, the general RL framework and especially Q-learning techniques, and a perfect example of extending RL learning with a built-in heuristic.},
	year = {2024},
	eissn = {1613-9178},
	pages = {1},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:34570694,
	title = {Machine learning -based decision support framework for CBRN protection},
	url = {https://m2.mtmt.hu/api/publication/34570694},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	doi = {10.1016/j.heliyon.2024.e25946},
	journal-iso = {HELIYON},
	journal = {HELIYON},
	volume = {10},
	unique-id = {34570694},
	year = {2024},
	eissn = {2405-8440},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Süle, Zoltán/0000-0002-5589-2355; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:33832252,
	title = {Az információmenedzsment szerepe az ABV-védelemben},
	url = {https://m2.mtmt.hu/api/publication/33832252},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	doi = {10.32561/nsz.2023.1.5},
	journal-iso = {NEMZETBIZT SZLE},
	journal = {NEMZETBIZTONSÁGI SZEMLE (ONLINE)},
	volume = {11},
	unique-id = {33832252},
	abstract = {Az atom-, bio- és vegyi (ABV-) incidensek felderítése kiemelt fontosságú feladat, amely évtizedek óta intenzíven kutatott téma. A folyamatos technológiai, adatfeldolgozási és automatizálási vívmányok újabb és újabb fejlesztési potenciált nyitnak az ABV-védelem terén is, amely napjainkra komplex, interdiszciplináris tudományterületté vált. Ennek megfelelően kémikusok, fizikusok, meteorológusok, katonai szakértők, programozók és adattudósok egyaránt közreműködnek a kutatásokban. A hazai ABV-védelmi képességek hatékony növelésének a kulcsa is abban rejlik, hogy megfelelően strukturált koncepció mentén folyamatos és célirányos fejlesztés történjen. Kutatásunk célja, hogy áttekintést adjunk a modern ABV-védelmi technológiák főbb komponenseiről, ezen belül összefoglaljuk az ABV-felderítés, illetve a döntéstámogatási lépések koncepcionális követelményeit, és bemutatjuk az információmenedzsment szerepét és legújabb lehetőségeit a folyamatokban.},
	year = {2023},
	eissn = {2064-3756},
	pages = {62-77},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:33714031,
	title = {Software Framework and Graph-based Methodology for Optimal Patient Appointment Planning},
	url = {https://m2.mtmt.hu/api/publication/33714031},
	author = {Süle, Zoltán and Baumgartner, János and Leitold, Dániel and Dulai, Tibor and Orosz, Ákos and Fogarassyné Vathy, Ágnes},
	doi = {10.1016/j.procs.2023.01.398},
	journal-iso = {PROC COMPUTER SCI},
	journal = {PROCEDIA COMPUTER SCIENCE},
	volume = {219},
	unique-id = {33714031},
	issn = {1877-0509},
	year = {2023},
	pages = {1169-1176},
	orcid-numbers = {Fogarassyné Vathy, Ágnes/0000-0002-5524-1675}
}

@inproceedings{MTMT:33067088,
	title = {Incorporation of heuristic search into Q-learning},
	url = {https://m2.mtmt.hu/api/publication/33067088},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	booktitle = {Short papers of VOCAL 2022 (9th VOCAL Optimization Conference: Advanced Algorithms)},
	unique-id = {33067088},
	abstract = {In the last years, Reinforcement Learning (RL) methods have proven its efficiency on multiple complex problems. For discrete problems Q-learning methods delivered an easily implementable solution. In this context a major challenge is to find a proper ratio between exploiting the current knowledge and exploring unknown patterns. For exploration, usually a purely random action taking mechanism is applied, which leads to a slow convergence to an optimal solution. In our presentation we will take an overview how different heuristics were built-in into RL methods to improve their learning efficiency, and we will present a categorization of the different approaches. Then we will demonstrate the effect of incorporating selected heuristic into a standard Q-learning based solution on a disassembly line optimisation problem.},
	year = {2022},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:33020481,
	title = {Scheduling Under Uncertainty for Industry 4.0 and 5.0},
	url = {https://m2.mtmt.hu/api/publication/33020481},
	author = {Bakon, Krisztián Attila and Holczinger, Tibor and Süle, Zoltán and Jaskó, Szilárd and Abonyi, János},
	doi = {10.1109/ACCESS.2022.3191426},
	journal-iso = {IEEE ACCESS},
	journal = {IEEE ACCESS},
	volume = {10},
	unique-id = {33020481},
	issn = {2169-3536},
	year = {2022},
	eissn = {2169-3536},
	pages = {74977-75017},
	orcid-numbers = {Bakon, Krisztián Attila/0000-0003-1882-094X; Holczinger, Tibor/0000-0003-4427-9253; Abonyi, János/0000-0001-8593-1493}
}

@article{MTMT:32517499,
	title = {The Applicability of Reinforcement Learning Methods in the Development of Industry 4.0 Applications},
	url = {https://m2.mtmt.hu/api/publication/32517499},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	doi = {10.1155/2021/7179374},
	journal-iso = {COMPLEXITY},
	journal = {COMPLEXITY},
	volume = {2021},
	unique-id = {32517499},
	issn = {1076-2787},
	year = {2021},
	eissn = {1099-0526},
	pages = {1-31},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Abonyi, János/0000-0001-8593-1493}
}

@CONFERENCE{MTMT:32176984,
	title = {Szétszerelési láncok optimálisa megerősítéses tanulással},
	url = {https://m2.mtmt.hu/api/publication/32176984},
	author = {Kegyes, Tamás and Süle, Zoltán and Abonyi, János},
	booktitle = {XXXIV. Magyar Operációkutatási Konferencia: Absztraktok könyve},
	unique-id = {32176984},
	year = {2021},
	pages = {111},
	orcid-numbers = {Kegyes, Tamás/0000-0002-9003-7776; Abonyi, János/0000-0001-8593-1493}
}

@CONFERENCE{MTMT:32176983,
	title = {Betegellátási folyamatok optimális ütemezése},
	url = {https://m2.mtmt.hu/api/publication/32176983},
	author = {Süle, Zoltán and Baumgartner, János and Fogarassyné Vathy, Ágnes},
	booktitle = {XXXIV. Magyar Operációkutatási Konferencia: Absztraktok könyve},
	unique-id = {32176983},
	year = {2021},
	pages = {61},
	orcid-numbers = {Fogarassyné Vathy, Ágnes/0000-0002-5524-1675}
}