{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:05:03Z","timestamp":1779689103710,"version":"3.53.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62136003"],"award-info":[{"award-number":["No.62136003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62136003"],"award-info":[{"award-number":["No.62136003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62136003"],"award-info":[{"award-number":["No.62136003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s12559-026-10602-w","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T05:55:52Z","timestamp":1779688552000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Equipping With Cognition: A Metacognition-Inspired Reinforcement Learning Approach for Multiobjective Safety-Critical Systems"],"prefix":"10.1007","volume":"18","author":[{"given":"Zhibin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiqun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"10602_CR1","unstructured":"Sutton RS, Barto AG, et\u00a0al. Reinforcement learning: An introduction. vol.\u00a01. MIT press Cambridge; 1998."},{"issue":"7553","key":"10602_CR2","first-page":"436","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning nature. 2015;521(7553):436\u201344.","journal-title":"Deep learning. nature."},{"issue":"7540","key":"10602_CR3","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529\u201333.","journal-title":"Nature."},{"key":"10602_CR4","unstructured":"Berner C, Brockman G, Chan B, Cheung V, D\u0119biak P, Dennison C, et\u00a0al. Dota 2 with Large Scale Deep Reinforcement Learning. Available from: arXiv:1912.06680."},{"issue":"2","key":"10602_CR5","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1109\/TCDS.2019.2948025","volume":"13","author":"S Abdelfattah","year":"2021","unstructured":"Abdelfattah S, Merrick K, Hu J. Intrinsically Motivated Hierarchical Policy Learning in Multiobjective Markov Decision Processes. IEEE Transactions on Cognitive and Developmental Systems. 2021;13(2):262\u201373. https:\/\/doi.org\/10.1109\/TCDS.2019.2948025.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems."},{"issue":"3","key":"10602_CR6","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1109\/TSMC.2014.2358639","volume":"45","author":"C Liu","year":"2015","unstructured":"Liu C, Xu X, Hu D. Multiobjective Reinforcement Learning: A Comprehensive Overview. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2015;45(3):385\u201398. https:\/\/doi.org\/10.1109\/TSMC.2014.2358639.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems."},{"key":"10602_CR7","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/BF02212307","volume":"7","author":"G Schraw","year":"1995","unstructured":"Schraw G, Moshman D. Metacognitive theories Educational psychology review. 1995;7:351\u201371.","journal-title":"Metacognitive theories. Educational psychology review."},{"key":"10602_CR8","first-page":"13","volume-title":"Metacognitive knowledge in theory","author":"J van Velzen","year":"2016","unstructured":"van Velzen J, van Velzen J. Metacognitive knowledge in theory. Metacognitive learning: Advancing learning by developing general knowledge of the learning process; 2016. p. 13\u201325."},{"issue":"3","key":"10602_CR9","doi-asserted-by":"publisher","first-page":"4178","DOI":"10.1109\/TITS.2024.3520514","volume":"26","author":"X Hou","year":"2025","unstructured":"Hou X, Gan M, Wu W, Ji Y, Zhao S, Chen J. Equipping With Cognition: Interactive Motion Planning Using Metacognitive-Attribution Inspired Reinforcement Learning for Autonomous Vehicles. IEEE Transactions on Intelligent Transportation Systems. 2025;26(3):4178\u201391. https:\/\/doi.org\/10.1109\/TITS.2024.3520514.","journal-title":"IEEE Transactions on Intelligent Transportation Systems."},{"issue":"2","key":"10602_CR10","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s10648-017-9413-7","volume":"30","author":"Moshman D Metacognitive","year":"2018","unstructured":"Metacognitive Moshman D, Revisited Theories. Educational Psychology Review. 2018;30(2):599\u2013606.","journal-title":"Educational Psychology Review."},{"issue":"8","key":"10602_CR11","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1038\/s41562-022-01332-8","volume":"6","author":"F Callaway","year":"2022","unstructured":"Callaway F, van Opheusden B, Gul S, Das P, Krueger PM, Griffiths TL, et al. Rational use of cognitive resources in human planning. Nature Human Behaviour. 2022;6(8):1112\u201325.","journal-title":"Nature Human Behaviour."},{"key":"10602_CR12","doi-asserted-by":"crossref","unstructured":"van Opheusden B, Galbiati G, Kuperwajs I, Bnaya Z, Li Y, Ji W. Revealing the impact of expertise on human planning with a two-player board game; 2021. Available from: https:\/\/api.semanticscholar.org\/CorpusID:236744082.","DOI":"10.31234\/osf.io\/rhq5j"},{"key":"10602_CR13","doi-asserted-by":"crossref","unstructured":"Krusche MJ, Schulz E, Guez A, Speekenbrink M. Adaptive planning in human search. bioRxiv. 2018;p. 268938.","DOI":"10.1101\/268938"},{"issue":"3","key":"10602_CR14","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TIT.1956.1056797","volume":"2","author":"A Newell","year":"1956","unstructured":"Newell A, Simon H. The logic theory machine-A complex information processing system. IRE Transactions on Information Theory. 1956;2(3):61\u201379. https:\/\/doi.org\/10.1109\/TIT.1956.1056797.","journal-title":"IRE Transactions on Information Theory."},{"issue":"3","key":"10602_CR15","doi-asserted-by":"publisher","first-page":"2152","DOI":"10.1109\/TSG.2016.2607801","volume":"9","author":"XS Zhang","year":"2018","unstructured":"Zhang XS, Li Q, Yu T, Yang B. Consensus Transfer $${Q}$$ -Learning for Decentralized Generation Command Dispatch Based on Virtual Generation Tribe. IEEE Transactions on Smart Grid. 2018;9(3):2152\u201365. https:\/\/doi.org\/10.1109\/TSG.2016.2607801.","journal-title":"IEEE Transactions on Smart Grid."},{"key":"10602_CR16","unstructured":"Berducci L, Aguilar EA, Ni\u010dkovi\u0107 D, Grosu R. Hierarchical Potential-based Reward Shaping from Task Specifications. Available from: arXiv:2110.02792."},{"key":"10602_CR17","doi-asserted-by":"crossref","unstructured":"Zhao Y, Chen Q, Hu W. Multi-objective reinforcement learning algorithm for MOSDMP in unknown environment. In: 2010 8th World Congress on Intelligent Control and Automation; 2010. p. 3190\u20133194.","DOI":"10.1109\/WCICA.2010.5553980"},{"key":"10602_CR18","doi-asserted-by":"crossref","unstructured":"Geibel P. Reinforcement learning for MDPs with constraints. In: Machine Learning: ECML 2006: 17th European Conference on Machine Learning Berlin, Germany, September 18-22, 2006 Proceedings 17. Springer; 2006. p. 646\u2013653.","DOI":"10.1007\/11871842_63"},{"key":"10602_CR19","doi-asserted-by":"crossref","unstructured":"Liao HL, Wu QH, Jiang L. Multi-objective optimization by reinforcement learning for power system dispatch and voltage stability. In: 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe); 2010. p. 1\u20138.","DOI":"10.1109\/ISGTEUROPE.2010.5638914"},{"key":"10602_CR20","doi-asserted-by":"crossref","unstructured":"Castelletti A, Pianosi F, Restelli M. Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems. In: The 2012 International Joint Conference on Neural Networks (IJCNN); 2012. p. 1\u20138.","DOI":"10.1109\/IJCNN.2012.6252759"},{"key":"10602_CR21","first-page":"325","volume":"5","author":"S Mannor","year":"2004","unstructured":"Mannor S, Shimkin N. A Geometric Approach to Multi-Criterion Reinforcement Learning. J Mach Learn Res. 2004;5:325\u201360.","journal-title":"J Mach Learn Res."},{"key":"10602_CR22","doi-asserted-by":"publisher","unstructured":"Barrett L, Narayanan S. Learning all optimal policies with multiple criteria. In: Proceedings of the 25th International Conference on Machine Learning. ICML \u201908. New York, NY, USA: Association for Computing Machinery; 2008. p. 41\u201347. Available from: https:\/\/doi.org\/10.1145\/1390156.1390162.","DOI":"10.1145\/1390156.1390162"},{"key":"10602_CR23","unstructured":"Yang R, Sun X, Narasimhan K. A generalized algorithm for multi-objective reinforcement learning and policy adaptation. Advances in neural information processing systems. 2019;32."},{"key":"10602_CR24","doi-asserted-by":"crossref","unstructured":"Liu E, Wu YC, Huang X, Gao C, Wang RJ, Xue K, et\u00a0al. Pareto set learning for multi-objective reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence 2025;39:18789\u201318797.","DOI":"10.1609\/aaai.v39i18.34068"},{"issue":"1","key":"10602_CR25","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11409-022-09328-5","volume":"18","author":"MF Teng","year":"2023","unstructured":"Teng MF, Yue M. Metacognitive writing strategies, critical thinking skills, and academic writing performance: A structural equation modeling approach. Metacognition and Learning. 2023;18(1):237\u201360.","journal-title":"Metacognition and Learning."},{"issue":"2","key":"10602_CR26","doi-asserted-by":"publisher","first-page":"41","DOI":"10.31578\/jebs.v8i2.291","volume":"8","author":"M Bouknify","year":"2023","unstructured":"Bouknify M. Importance of metacognitive strategies in enhancing reading comprehension skills. J Educ Black Sea Region. 2023;8(2):41\u201351.","journal-title":"J Educ Black Sea Region."},{"key":"10602_CR27","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.plrev.2023.07.002","volume":"46","author":"I Lebuda","year":"2023","unstructured":"Lebuda I, Benedek M. A systematic framework of creative metacognition. Phys Life Rev. 2023;46:161\u201381.","journal-title":"Phys Life Rev."},{"key":"10602_CR28","doi-asserted-by":"crossref","unstructured":"Heindrich L, Consul S, Lieder F. An intelligent tutor for planning in large partially observable environments. Int J Artif Intell Educ. 2025;p. 1\u201333.","DOI":"10.1007\/s40593-025-00493-7"},{"key":"10602_CR29","unstructured":"Callaway F, Gul S, Krueger PM, Griffiths TL, Lieder F. Learning to select computations. Available from: arXiv:1711.06892."},{"issue":"5","key":"10602_CR30","doi-asserted-by":"publisher","first-page":"3195","DOI":"10.1109\/TSMC.2024.3358060","volume":"54","author":"J Senthilnath","year":"2024","unstructured":"Senthilnath J, Harikumar K, Sundaram S. Metacognitive Decision-Making Framework for Multi-UAV Target Search Without Communication. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2024;54(5):3195\u2013206. https:\/\/doi.org\/10.1109\/TSMC.2024.3358060.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems."},{"key":"10602_CR31","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning. Pmlr; 2018. p. 1861\u20131870."},{"issue":"12","key":"10602_CR32","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1002\/acs.3326","volume":"35","author":"A Mustafa","year":"2021","unstructured":"Mustafa A, Mazouchi M, Nageshrao S, Modares H. Assured learning-enabled autonomy: A metacognitive reinforcement learning framework. Int J Adapt Control Signal Proc. 2021;35(12):2348\u201371.","journal-title":"Int J Adapt Control Signal Proc."},{"issue":"02","key":"10602_CR33","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1142\/S0129065704001899","volume":"14","author":"M Seeger","year":"2004","unstructured":"Seeger M. Gaussian processes for machine learning. Int J Neural Syst. 2004;14(02):69\u2013106.","journal-title":"Int J Neural Syst."},{"key":"10602_CR34","unstructured":"Sutton RS, McAllester D, Singh S, Mansour Y. Policy gradient methods for reinforcement learning with function approximation. Adv Neural Inf Process Syst. 1999;12."},{"issue":"5","key":"10602_CR35","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/tit.2011.2182033","volume":"58","author":"N Srinivas","year":"2012","unstructured":"Srinivas N, Krause A, Kakade SM, Seeger MW. Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting. IEEE Trans Inf Theory. 2012;58(5):3250\u201365. https:\/\/doi.org\/10.1109\/tit.2011.2182033.","journal-title":"IEEE Trans Inf Theory."},{"issue":"3","key":"10602_CR36","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TPAMI.2022.3190471","volume":"45","author":"Q Li","year":"2023","unstructured":"Li Q, Peng Z, Feng L, Zhang Q, Xue Z, Zhou B. MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning. IEEE Trans Patt Anal Mach Intell. 2023;45(3):3461\u201375. https:\/\/doi.org\/10.1109\/TPAMI.2022.3190471.","journal-title":"IEEE Trans Patt Anal Mach Intell."},{"issue":"4","key":"10602_CR37","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1109\/TIV.2022.3209910","volume":"7","author":"G Sidorenko","year":"2022","unstructured":"Sidorenko G, Fedorov A, Thunberg J, Vinel A. Towards a complete safety framework for longitudinal driving. IEEE Trans Intell Vehicl. 2022;7(4):809\u201314.","journal-title":"IEEE Trans Intell Vehicl."},{"key":"10602_CR38","doi-asserted-by":"crossref","unstructured":"Nguyen HD, Kim D, Nguyen A, Han K, Vu MN. Safe trajectory optimization and efficient-offline robust model predictive control for autonomous vehicle lane change. IEEE Trans Intell Vehicle; 2024.","DOI":"10.1109\/TIV.2024.3467111"},{"issue":"2","key":"10602_CR39","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TITS.2020.3024655","volume":"23","author":"S Aradi","year":"2020","unstructured":"Aradi S. Survey of deep reinforcement learning for motion planning of autonomous vehicles. IEEE Trans Intell Trans Syst. 2020;23(2):740\u201359.","journal-title":"IEEE Trans Intell Trans Syst."},{"issue":"1","key":"10602_CR40","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1109\/TIV.2023.3329785","volume":"9","author":"F Dang","year":"2023","unstructured":"Dang F, Chen D, Chen J, Li Z. Event-triggered model predictive control with deep reinforcement learning for autonomous driving. IEEE Trans Intell Vehicl. 2023;9(1):459\u201368.","journal-title":"IEEE Trans Intell Vehicl."}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10602-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-026-10602-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-026-10602-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T05:55:54Z","timestamp":1779688554000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-026-10602-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10602"],"URL":"https:\/\/doi.org\/10.1007\/s12559-026-10602-w","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,25]]},"assertion":[{"value":"14 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"60"}}