{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T11:58:12Z","timestamp":1773403092989,"version":"3.50.1"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006595","name":"Unitatea Executiva pentru Finantarea Invatamantului Superior a Cercetarii Dezvoltarii si Inovarii","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1016\/j.asoc.2024.111687","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T15:50:56Z","timestamp":1714751456000},"page":"111687","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":58,"special_numbering":"C","title":["Adaptive reinforcement learning-based control using proximal policy optimization and slime mould algorithm with experimental tower crane system validation"],"prefix":"10.1016","volume":"160","author":[{"given":"Iuliu Alexandru","family":"Zamfirache","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2060-7403","authenticated-orcid":false,"given":"Radu-Emil","family":"Precup","sequence":"additional","affiliation":[]},{"given":"Emil M.","family":"Petriu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2024.111687_bib1","series-title":"Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science","author":"Montavon","year":"2012"},{"key":"10.1016\/j.asoc.2024.111687_bib2","unstructured":"J. Schulman, S. Levine, P. Abbeel, M. Jordan, P. Moritz, Trust region policy optimization. In: Proc. 32nd International Conference on Machine Learning, Lille, France, 2015, pp. 1889\u20131897."},{"key":"10.1016\/j.asoc.2024.111687_bib3","first-page":"2017","article-title":"Proximal policy optimization algorithms","volume":"06347","author":"Schulman","year":"1707","journal-title":"arXiv"},{"issue":"1","key":"10.1016\/j.asoc.2024.111687_bib4","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s10994-006-8365-9","article-title":"Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming","volume":"65","author":"George","year":"2006","journal-title":"Mach. Learn."},{"key":"10.1016\/j.asoc.2024.111687_bib5","doi-asserted-by":"crossref","unstructured":"L.N. Smith, Cyclical learning rates for training neural networks. In: Proc. 2017 IEEE Winter Conference on Applications of Computer Vision, Santa Rosa, CA, USA, 2017, pp. 464\u2013472.","DOI":"10.1109\/WACV.2017.58"},{"key":"10.1016\/j.asoc.2024.111687_bib6","article-title":"Adadelta: an adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212. 5701"},{"key":"10.1016\/j.asoc.2024.111687_bib7","unstructured":"T. Schaul, S.-X. Zhang, Y. LeCun, No more pesky learning rates. In: Proc. 30th International Conference on Machine Learning, Atlanta GA, USA, 2013, pp. 343\u2013351."},{"key":"10.1016\/j.asoc.2024.111687_bib8","series-title":"Nature-inspired Optimization Algorithms for Fuzzy Controlled Servo Systems","author":"Precup","year":"2019"},{"key":"10.1016\/j.asoc.2024.111687_bib9","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.compind.2015.03.001","article-title":"An overview on fault diagnosis and nature-inspired optimal control of industrial process applications","volume":"74","author":"Precup","year":"2015","journal-title":"Comput. Ind."},{"key":"10.1016\/j.asoc.2024.111687_bib10","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108624","article-title":"Adaptive evolution strategy with ensemble of mutations for reinforcement learning","volume":"245","author":"Ajani","year":"2022","journal-title":"Knowl. -Based Syst."},{"key":"10.1016\/j.asoc.2024.111687_bib11","doi-asserted-by":"crossref","unstructured":"A. Sehgal, H. La, S. Louis, H. Nguyen, Deep reinforcement learning using genetic algorithm for parameter optimization. In: Proc. 2019 3rd IEEE International Conference on Robotic Computing, Naples, Italy, 2019, pp. 596\u2013601.","DOI":"10.1109\/IRC.2019.00121"},{"key":"10.1016\/j.asoc.2024.111687_bib12","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.engappai.2018.09.007","article-title":"Interpretable policies for reinforcement learning by genetic programming","volume":"76","author":"Hein","year":"2018","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2024.111687_bib13","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.ins.2021.11.051","article-title":"Policy iteration reinforcement learning-based control using a grey wolf optimizer algorithm","volume":"585","author":"Zamfirache","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2024.111687_bib14","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ins.2021.10.070","article-title":"Reinforcement Learning-based control using Q-learning and gravitational search algorithm with experimental validation on a nonlinear servo system","volume":"583","author":"Zamfirache","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2024.111687_bib15","article-title":"Neural network-based control using actor-critic reinforcement learning and grey wolf optimizer with experimental servo system validation","volume":"225","author":"Zamfirache","year":"2023","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"10.1016\/j.asoc.2024.111687_bib16","first-page":"615","article-title":"Q-learning, policy iteration and actor-critic reinforcement learning combined with metaheuristic algorithms in servo system control","volume":"21","author":"Zamfirache","year":"2023","journal-title":"Facta Univ., Ser.: Mech. Eng."},{"key":"10.1016\/j.asoc.2024.111687_bib17","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.future.2020.03.055","article-title":"Slime mould algorithm: a new method for stochastic optimization","volume":"111","author":"Li","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.asoc.2024.111687_bib18","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105363","article-title":"Interval type-3 fuzzy fractal approach in sound speaker quality control evaluation","volume":"116","author":"Castillo","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2024.111687_bib19","doi-asserted-by":"crossref","unstructured":"J. Vascak, P. Kovacik, K. Hirota, P. Sincak, Performance-based adaptive fuzzy control of aircrafts. In: Proc. 10th IEEE International Conference on Fuzzy Systems, Melbourne, VIC, Australia, 2001, vol. 3, pp. 761\u2013764.","DOI":"10.1109\/FUZZ.2001.1009066"},{"key":"10.1016\/j.asoc.2024.111687_bib20","doi-asserted-by":"crossref","unstructured":"J. Va\u0161\u010d\u00e1k, J. Hvizdo\u0161, M. Puheim, Agent-based cloud computing systems for traffic management. In: Proc. 2016 International Conference on Intelligent Networking and Collaborative Systems, Ostrava, Czech Republic, 2016, pp. 73\u201379.","DOI":"10.1109\/INCoS.2016.80"},{"key":"10.1016\/j.asoc.2024.111687_bib21","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/j.ins.2022.11.143","article-title":"Prioritization of unmanned aerial vehicles in transportation systems using the integrated stratified fuzzy rough decision-making approach with the Hamacher operator","volume":"622","author":"Pamucar","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2024.111687_bib22","doi-asserted-by":"crossref","unstructured":"J. Hvizdo\u0161, J. Va\u0161\u010d\u00e1k, A. B\u0159ezina, Object identification and localization by smart floors. In: Proc. IEEE 19th International Conference on Intelligent Engineering Systems, Bratislava, Slovakia, 2015, pp. 113\u2013117.","DOI":"10.1109\/INES.2015.7329649"},{"key":"10.1016\/j.asoc.2024.111687_bib23","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.robot.2014.09.034","article-title":"A novel pose estimation algorithm for robotic navigation","volume":"63","author":"Pozna","year":"2015","journal-title":"Robot. Auton. Syst."},{"issue":"9","key":"10.1016\/j.asoc.2024.111687_bib24","doi-asserted-by":"crossref","first-page":"8502","DOI":"10.1109\/TVT.2019.2927124","article-title":"Optimal constant acceleration motion primitives","volume":"68","author":"Klan\u010dar","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.asoc.2024.111687_bib25","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.arcontrol.2021.04.008","article-title":"A decision-making framework for dynamic scheduling of cyber-physical production systems based on digital twins","volume":"51","author":"Villalonga","year":"2021","journal-title":"Annu. Rev. Control"},{"issue":"1","key":"10.1016\/j.asoc.2024.111687_bib26","first-page":"100","article-title":"Development of microcomputers and motor control software for steel pipe cutting units","volume":"26","author":"Mili\u0107evi\u0107","year":"2023","journal-title":"Rom. J. Inf. Sci. Technol."},{"issue":"3","key":"10.1016\/j.asoc.2024.111687_bib27","first-page":"378","article-title":"Fuzzy control solution for telesurgical applications","volume":"11","author":"Precup","year":"2012","journal-title":"Appl. Comput. Math."},{"key":"10.1016\/j.asoc.2024.111687_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102721","article-title":"Multi-task learning framework to predict the status of central venous catheter based on radiographs","volume":"146","author":"Wang","year":"2023","journal-title":"Artif. Intell. Med."},{"issue":"1","key":"10.1016\/j.asoc.2024.111687_bib29","first-page":"49","article-title":"New opportunities model for monitoring, analyzing and forecasting the official statistics on coronavirus disease pandemic","author":"Abramov","year":"2023","journal-title":"Rom. J. Inf. Sci. Technol. 26"},{"key":"10.1016\/j.asoc.2024.111687_bib30","doi-asserted-by":"crossref","unstructured":"E. Osaba, E. Villar-Rodriguez, I. Oregi, A. Moreno-Fernandez-de-Leceta, Hybrid quantum computing-tabu search algorithm for partitioning problems: preliminary study on the traveling salesman problem. In: Proc. 2021 IEEE Congress on Evolutionary Computation, Krak\u00f3w, Poland, 2021, pp. 351\u2013358.","DOI":"10.1109\/CEC45853.2021.9504923"},{"issue":"3","key":"10.1016\/j.asoc.2024.111687_bib31","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/LCSYS.2020.2981895","article-title":"Torque vectoring for high-performance electric vehicles: a data-driven MPC approach","volume":"4","author":"Lucchini","year":"2020","journal-title":"IEEE Control Syst. Lett."},{"key":"10.1016\/j.asoc.2024.111687_bib32","series-title":"Data-Driven Model-Free Controllers","author":"Precup","year":"2021"},{"issue":"3","key":"10.1016\/j.asoc.2024.111687_bib34","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1002\/asjc.2494","article-title":"Tensor product-based model transformation approach to tower crane systems modeling","volume":"23","author":"Hedrea","year":"2021","journal-title":"Asian J. Control"},{"key":"10.1016\/j.asoc.2024.111687_bib35","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.ejcon.2020.08.001","article-title":"Hybrid data-driven fuzzy active disturbance rejection control for tower crane systems","volume":"58","author":"Roman","year":"2021","journal-title":"Eur. J. Control"},{"key":"10.1016\/j.asoc.2024.111687_bib36","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2017"},{"key":"10.1016\/j.asoc.2024.111687_bib37","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1002\/j.1537-2197.1931.tb09577.x","article-title":"The life history of Physarum polycephalum","volume":"18","author":"Howard","year":"1931","journal-title":"Am. J. Bot."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494624004617?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494624004617?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:38:11Z","timestamp":1731890291000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494624004617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":36,"alternative-id":["S1568494624004617"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2024.111687","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive reinforcement learning-based control using proximal policy optimization and slime mould algorithm with experimental tower crane system validation","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2024.111687","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"111687"}}