{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:00:42Z","timestamp":1785391242910,"version":"3.55.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.asoc.2026.115800","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:12:37Z","timestamp":1781968357000},"page":"115800","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["An intelligent reinforcement learning framework for sequential decision-making"],"prefix":"10.1016","volume":"202","author":[{"given":"Yigit Cagatay","family":"Kuyu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115800_bib0005","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.asoc.2026.115800_bib0010","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"10.1016\/j.asoc.2026.115800_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110990","article-title":"Artificial neural network aided computing for two dimensional magnetohydrodynamic peristaltic movement of nanofluid with heat and mass transfer","volume":"154","author":"Alahmadi","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115800_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.csite.2025.106812","article-title":"AI-powered analysis of thermally magnetized EMHD casson hybrid nanofluid","author":"Zia","year":"2025","journal-title":"Case Stud. Therm. Eng."},{"key":"10.1016\/j.asoc.2026.115800_bib0025","doi-asserted-by":"crossref","DOI":"10.1063\/5.0254068","article-title":"Bayesian regularization-based intelligent computing for peristaltic propulsion of curvature-dependent channel walls","volume":"37","author":"Iqbal","year":"2025","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.asoc.2026.115800_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.molliq.2024.126783","article-title":"Integration of artificial neural network computing for radially magnetized bioconvection peristaltic movement of reiner-philippoff nanofluid with porous medium","volume":"419","author":"Iqbal","year":"2025","journal-title":"J. Mol. Liq."},{"key":"10.1016\/j.asoc.2026.115800_bib0035","doi-asserted-by":"crossref","DOI":"10.1615\/JPorMedia.2025057165","article-title":"Machine learning computations for MHD bioconvection peristaltic transport of non-newtonian nanofluid flow containing gyrotactic microorganisms with porous medium","volume":"28","author":"Iqbal","year":"2025","journal-title":"Journal of Porous Media"},{"key":"10.1016\/j.asoc.2026.115800_bib0040","doi-asserted-by":"crossref","DOI":"10.1063\/5.0207600","article-title":"Heat transfer analysis for magnetohydrodynamic peristalsis of reiner\u2013philippoff fluid: application of an artificial neural network","volume":"36","author":"Iqbal","year":"2024","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.asoc.2026.115800_bib0045","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.asoc.2026.115800_bib0050","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The arcade learning environment: an evaluation platform for general agents","volume":"47","author":"Bellemare","year":"2013","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.asoc.2026.115800_bib0055","doi-asserted-by":"crossref","first-page":"2063","DOI":"10.1109\/TNNLS.2018.2790388","article-title":"Applications of deep learning and reinforcement learning to biological data","volume":"29","author":"Mahmud","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115800_bib0060","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1007\/s11370-021-00398-z","article-title":"A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning","volume":"14","author":"Morales","year":"2021","journal-title":"Intell. Serv. Robot."},{"key":"10.1016\/j.asoc.2026.115800_bib0065","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: a survey","volume":"23","author":"Kiran","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115800_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2020.101964","article-title":"Reinforcement learning for intelligent healthcare applications: a survey","volume":"109","author":"Coronato","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.asoc.2026.115800_bib0075","series-title":"International Conference on Machine Learning","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"Chebotar","year":"2017"},{"key":"10.1016\/j.asoc.2026.115800_bib0080","series-title":"Intelligent Transportation Systems Conference","first-page":"277","article-title":"Model-free deep reinforcement learning for urban autonomous driving","author":"Chen","year":"2019"},{"key":"10.1016\/j.asoc.2026.115800_bib0085","doi-asserted-by":"crossref","first-page":"14458","DOI":"10.1109\/TVT.2020.3040398","article-title":"An integrated framework of decision making and motion planning for autonomous vehicles considering social behaviors","volume":"69","author":"Hang","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.asoc.2026.115800_bib0090","doi-asserted-by":"crossref","first-page":"186474","DOI":"10.1109\/ACCESS.2020.3029868","article-title":"Research on adaptive job shop scheduling problems based on dueling double DQN","volume":"8","author":"Han","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115800_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.108063","article-title":"Prognostics and health management: a review from the perspectives of design, development and decision","volume":"217","author":"Hu","year":"2022","journal-title":"Reliability Engineering-System Safety"},{"key":"10.1016\/j.asoc.2026.115800_bib0100","doi-asserted-by":"crossref","first-page":"276","DOI":"10.3390\/make4010013","article-title":"Robust reinforcement learning: a review of foundations and recent advances","volume":"4","author":"Moos","year":"2022","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"10.1016\/j.asoc.2026.115800_bib0105","series-title":"AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","first-page":"155","article-title":"A review of uncertainty for deep reinforcement learning","author":"Lockwood","year":"2022"},{"key":"10.1016\/j.asoc.2026.115800_bib0110","author":"Zhou"},{"key":"10.1016\/j.asoc.2026.115800_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.106886","article-title":"A review on reinforcement learning: introduction and applications in industrial process control","volume":"139","author":"Nian","year":"2020","journal-title":"Computers-Chemical Engineering"},{"key":"10.1016\/j.asoc.2026.115800_bib0120","series-title":"International Conference on Machine Learning","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","author":"Tessler","year":"2019"},{"key":"10.1016\/j.asoc.2026.115800_bib0125","doi-asserted-by":"crossref","first-page":"3153","DOI":"10.1109\/TPWRS.2023.3289334","article-title":"Model-free economic dispatch for virtual power plants: an adversarial safe reinforcement learning approach","volume":"39","author":"Yi","year":"2023","journal-title":"IEEE Trans. Power Syst."},{"key":"10.1016\/j.asoc.2026.115800_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2020.102949","article-title":"Model-free perimeter metering control for two-region urban networks using deep reinforcement learning","volume":"124","author":"Zhou","year":"2021","journal-title":"Transp. Res. C Emerg. Technol."},{"key":"10.1016\/j.asoc.2026.115800_bib0135","doi-asserted-by":"crossref","first-page":"2336","DOI":"10.1109\/TII.2020.3001095","article-title":"Model-free emergency frequency control based on reinforcement learning","volume":"17","author":"Chen","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.asoc.2026.115800_bib0140","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.3390\/pr11082269","article-title":"Intelligent control of wastewater treatment plants based on model-free deep reinforcement learning","volume":"11","author":"Aponte-Rengifo","year":"2023","journal-title":"Processes"},{"key":"10.1016\/j.asoc.2026.115800_bib0145","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1109\/TSTE.2022.3226106","article-title":"Deep reinforcement learning based unit commitment scheduling under load and wind power uncertainty","volume":"14","author":"Ajagekar","year":"2022","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"10.1016\/j.asoc.2026.115800_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2021.121873","article-title":"Real-time optimal energy management of microgrid with uncertainties based on deep reinforcement learning","volume":"238","author":"Guo","year":"2022","journal-title":"Energy"},{"key":"10.1016\/j.asoc.2026.115800_bib0155","doi-asserted-by":"crossref","first-page":"5246","DOI":"10.1109\/TSG.2018.2879572","article-title":"Model-free real-time EV charging scheduling based on deep reinforcement learning","volume":"10","author":"Wan","year":"2018","journal-title":"IEEE Trans. Smart Grid"},{"key":"10.1016\/j.asoc.2026.115800_bib0160","doi-asserted-by":"crossref","first-page":"4840","DOI":"10.1109\/TPWRS.2022.3212938","article-title":"A novel model-free deep reinforcement learning framework for energy management of a PV integrated energy hub","volume":"38","author":"Dolatabadi","year":"2022","journal-title":"IEEE Trans. Power Syst."},{"key":"10.1016\/j.asoc.2026.115800_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2022.109747","article-title":"Towards self-learning control of HVAC systems with the consideration of dynamic occupancy patterns: application of model-free deep reinforcement learning","volume":"226","author":"Esrafilian-Najafabadi","year":"2022","journal-title":"Build. Environ."},{"key":"10.1016\/j.asoc.2026.115800_bib0170","doi-asserted-by":"crossref","first-page":"3928","DOI":"10.3390\/en13153928","article-title":"Deep reinforcement learning-based voltage control to deal with model uncertainties in distribution networks","volume":"13","author":"Toubeau","year":"2020","journal-title":"Energies"},{"key":"10.1016\/j.asoc.2026.115800_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.enbuild.2022.112594","article-title":"Model-free dynamic management strategy for low-carbon home energy based on deep reinforcement learning accommodating stochastic environment","volume":"278","author":"Hou","year":"2023","journal-title":"Energy Build."},{"key":"10.1016\/j.asoc.2026.115800_bib0180","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-12554-x","article-title":"Improving energy autonomy of positive energy districts using multi-agent deep reinforcement learning","volume":"15","author":"Hribar","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.asoc.2026.115800_bib0185","doi-asserted-by":"crossref","first-page":"2721","DOI":"10.1111\/mice.13228","article-title":"A learning-based method for optimal dynamic privileged parking permit policy","volume":"39","author":"Yuan","year":"2024","journal-title":"Comput.-aided Civ. Infrastruct. Eng."},{"key":"10.1016\/j.asoc.2026.115800_bib0190","doi-asserted-by":"crossref","first-page":"743","DOI":"10.35833\/MPCE.2021.000394","article-title":"Mixed deep reinforcement learning considering discrete-continuous hybrid action space for smart home energy management","volume":"10","author":"Huang","year":"2022","journal-title":"J. Mod. Power Syst. Clean Energy"},{"key":"10.1016\/j.asoc.2026.115800_bib0195","series-title":"Adaptive vessel routing in emission control areas under weather uncertainty: a robust deep Q-learning method","first-page":"743","author":"Lee","year":"2025"},{"key":"10.1016\/j.asoc.2026.115800_bib0200","series-title":"IEEE 6th World Forum on Internet of Things","first-page":"1","article-title":"Resource allocation in mobility-aware federated learning networks: a deep reinforcement learning approach","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.asoc.2026.115800_bib0205","series-title":"IEEE International Conference on Distributed Computing in Smart Systems and the Internet of Things","first-page":"669","article-title":"A deep Q-learning framework for enhanced QoE and energy optimization in fog computing","author":"Sumona","year":"2024"},{"key":"10.1016\/j.asoc.2026.115800_bib0210","author":"Schulman"},{"key":"10.1016\/j.asoc.2026.115800_bib0215","series-title":"International Conference on Machine Learning","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"10.1016\/j.asoc.2026.115800_bib0220","author":"Mnih"},{"key":"10.1016\/j.asoc.2026.115800_bib0225","series-title":"IEEE Symposium Series on Computational Intelligence","first-page":"745","article-title":"Optimizing agent training with deep Q-learning on a self-driving reinforcement learning environment","author":"Rodrigues","year":"2020"},{"key":"10.1016\/j.asoc.2026.115800_bib0230","series-title":"IEEE Information Theory and Applications Workshop","first-page":"1","article-title":"Efficient exploration through Bayesian deep Q-Networks","author":"Azizzadenesheli","year":"2018"},{"key":"10.1016\/j.asoc.2026.115800_bib0235","author":"Schaul"},{"key":"10.1016\/j.asoc.2026.115800_bib0240","author":"Brockman"},{"key":"10.1016\/j.asoc.2026.115800_bib0245","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/TCDS.2019.2957831","article-title":"An efficient unified approach using demonstrations for inverse reinforcement learning","volume":"13","author":"Hwang","year":"2019","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.asoc.2026.115800_bib0250","series-title":"IEEE International Conference on Signal Processing and Integrated Networks","first-page":"78","article-title":"Empirical study of deep reinforcement learning algorithms for cartpole problem","author":"Kumar","year":"2024"},{"key":"10.1016\/j.asoc.2026.115800_bib0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.swevo.2011.02.002","article-title":"A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms","volume":"1","author":"Derrac","year":"2011","journal-title":"Swarm Evol. Comput."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012482?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012482?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:16:15Z","timestamp":1785388575000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626012482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":51,"alternative-id":["S1568494626012482"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115800","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An intelligent reinforcement learning framework for sequential decision-making","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115800","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115800"}}