{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:04Z","timestamp":1793608084319,"version":"4.5.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682025CX080"],"award-info":[{"award-number":["2682025CX080"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682025XJ007"],"award-info":[{"award-number":["2682025XJ007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012551","name":"Sichuan Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2026YFHZ0235"],"award-info":[{"award-number":["2026YFHZ0235"]}],"id":[{"id":"10.13039\/100012551","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012551","name":"Sichuan Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2026YFHZ0221"],"award-info":[{"award-number":["2026YFHZ0221"]}],"id":[{"id":"10.13039\/100012551","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2568231"],"award-info":[{"award-number":["U2568231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303095"],"award-info":[{"award-number":["62303095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109685","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T15:04:58Z","timestamp":1790348698000},"page":"109685","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Transfer learning-based safe Q-learning for discrete-time nonlinear systems with asymmetric state constraints"],"prefix":"10.1016","volume":"206","author":[{"given":"Jiaoyuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minglei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8022-907X","authenticated-orcid":false,"given":"Dawei","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109685_bib0001","series-title":"Reinforcement learning and optimal control","volume":"vol. 1)","author":"Bertsekas","year":"2019"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.23919\/AISE.2026.000001","article-title":"Toward collaborative and adaptive learning: A survey of multi-agent reinforcement learning in education","volume":"2","author":"Bouguettaya","year":"2026","journal-title":"Artificial Intelligence Science and Engineering"},{"issue":"9","key":"10.1016\/j.neunet.2026.109685_bib0003","doi-asserted-by":"crossref","first-page":"4905","DOI":"10.1109\/TNNLS.2026.3672136","article-title":"Policy-adjustable q-learning for data-driven nonlinear optimal tracking control","volume":"37","author":"Chen","year":"2026","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0004","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.1109\/TNNLS.2023.3326867","article-title":"Safe adaptive policy transfer reinforcement learning for distributed multiagent control","volume":"36","author":"Du","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.109685_bib0005","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1109\/TNNLS.2018.2806347","article-title":"Robust ADP design for continuous-time nonlinear systems with output constraints","volume":"29","author":"Fan","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"8","key":"10.1016\/j.neunet.2026.109685_bib0006","doi-asserted-by":"crossref","first-page":"12572","DOI":"10.1109\/TITS.2021.3115240","article-title":"Multi-agent transfer reinforcement learning with multi-view encoder for adaptive traffic signal control","volume":"23","author":"Ge","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.109685_bib0007","doi-asserted-by":"crossref","first-page":"8076","DOI":"10.1016\/j.ifacol.2020.12.2276","article-title":"Safe reinforcement learning via projection on a safe set: How to achieve optimality?","volume":"53","author":"Gros","year":"2020","journal-title":"IFAC-PapersOnLine"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0008","doi-asserted-by":"crossref","first-page":"20","DOI":"10.23919\/AISE.2026.000002","article-title":"Robust reinforcement learning: Methods, benchmarks and challenges","volume":"2","author":"Gu","year":"2026","journal-title":"Artificial Intelligence Science and Engineering"},{"issue":"12","key":"10.1016\/j.neunet.2026.109685_bib0009","doi-asserted-by":"crossref","first-page":"11216","DOI":"10.1109\/TPAMI.2024.3457538","article-title":"A review of safe reinforcement learning: Methods, theories and applications","volume":"46","author":"Gu","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109685_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106737","article-title":"Adp-based fault-tolerant consensus control for multiagent systems with irregular state constraints","volume":"180","author":"Guo","year":"2024","journal-title":"Neural Networks"},{"issue":"5","key":"10.1016\/j.neunet.2026.109685_bib0011","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1109\/TAC.1969.1099283","article-title":"A transformation technique for optimal control problems with a state variable inequality constraint","volume":"14","author":"Jacobson","year":"1969","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/j.neunet.2026.109685_bib0012","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"Journal of artificial intelligence research"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0013","doi-asserted-by":"crossref","first-page":"13528","DOI":"10.3182\/20110828-6-IT-1002.02232","article-title":"A novel q-learning based adaptive optimal controller implementation for a humanoid robotic arm","volume":"44","author":"Khan","year":"2011","journal-title":"IFAC Proceedings Volumes"},{"key":"10.1016\/j.neunet.2026.109685_bib0014","series-title":"2015 54th IEEE Conference on decision and control (CDC)","first-page":"7554","article-title":"Revived transformation for nonlinear systems subject to state constraints","author":"Kimura","year":"2015"},{"issue":"5","key":"10.1016\/j.neunet.2026.109685_bib0015","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1109\/TNNLS.2018.2861945","article-title":"Off-policy interleaved q-learning: Optimal control for affine nonlinear discrete-time systems","volume":"30","author":"Li","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109685_bib0016","series-title":"2021\u202fIEEE Sustainable power and energy conference (iSPEC)","first-page":"632","article-title":"Load frequency control strategy of island microgrid with flexible resources based on DQN","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109685_bib0017","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1016\/j.neucom.2022.11.006","article-title":"Safe reinforcement learning for affine nonlinear systems with state constraints and input saturation using control barrier functions","volume":"518","author":"Liu","year":"2023","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.neunet.2026.109685_bib0018","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1002\/rnc.5132","article-title":"Safe reinforcement learning: A control barrier function optimization approach","volume":"31","author":"Marvi","year":"2021","journal-title":"International Journal of Robust and Nonlinear Control"},{"issue":"2024","key":"10.1016\/j.neunet.2026.109685_bib0019","article-title":"A survey on load frequency control using reinforcement learning-based data-driven controller","volume":"166","author":"Muduli","year":"2024","journal-title":"Applied Soft Computing"},{"issue":"2","key":"10.1016\/j.neunet.2026.109685_bib0020","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TSMC.2017.2777472","article-title":"A novel neural-network-based adaptive control scheme for output-constrained stochastic switched nonlinear systems","volume":"49","author":"Niu","year":"2017","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"10.1016\/j.neunet.2026.109685_bib0021","series-title":"Mathematical proceedings of the cambridge philosophical society","first-page":"406","article-title":"A generalized inverse for matrices","volume":"vol. 51","author":"Penrose","year":"1955"},{"issue":"4","key":"10.1016\/j.neunet.2026.109685_bib0022","doi-asserted-by":"crossref","first-page":"6257","DOI":"10.1109\/TII.2023.3344130","article-title":"Action-dependent heuristic dynamic programming with experience replay for wastewater treatment processes","volume":"20","author":"Qiao","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"3","key":"10.1016\/j.neunet.2026.109685_bib0023","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1109\/TSMC.1979.4310171","article-title":"An approximation theory of optimal control for trainable manipulators","volume":"9","author":"Saridis","year":"2007","journal-title":"IEEE Transactions on systems, Man, and Cybernetics"},{"key":"10.1016\/j.neunet.2026.109685_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120495","article-title":"Reinforcement learning algorithms: A brief survey","volume":"231","author":"Shakya","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0025","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TSMC.2022.3173275","article-title":"Online optimal event-triggered h\u221e control for nonlinear systems with constrained state and input","volume":"53","author":"Song","year":"2022","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"3","key":"10.1016\/j.neunet.2026.109685_bib0026","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1002\/rnc.7685","article-title":"Discrete-time optimal control of state-constrained nonlinear systems using approximate dynamic programming","volume":"35","author":"Song","year":"2025","journal-title":"International Journal of Robust and Nonlinear Control"},{"key":"10.1016\/j.neunet.2026.109685_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128370","article-title":"Convergence and stability analysis of value iteration q-learning under non-discounted cost for discrete-time optimal control","volume":"606","author":"Song","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0028","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1109\/TNNLS.2022.3178746","article-title":"Model-free optimal tracking control of nonlinear input-affine discrete-time systems via an iterative deterministic q-learning algorithm","volume":"35","author":"Song","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0029","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/TAC.2021.3049335","article-title":"Probabilistic model predictive safety certification for learning-based control","volume":"67","author":"Wabersich","year":"2021","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/j.neunet.2026.109685_bib0030","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.isatra.2020.10.001","article-title":"State transformation-based adaptive tracking control for a class of nonlinear systems with time-varying state constraints","volume":"110","author":"Wang","year":"2021","journal-title":"ISA Transactions"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0031","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/JAS.2023.123843","article-title":"Recent progress in reinforcement learning and adaptive dynamic programming for advanced control applications","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"10.1016\/j.neunet.2026.109685_bib0032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"Journal of Big data"},{"issue":"6","key":"10.1016\/j.neunet.2026.109685_bib0033","doi-asserted-by":"crossref","first-page":"3408","DOI":"10.1002\/rnc.5955","article-title":"Adaptive dynamic programming for optimal control of discrete-time nonlinear system with state constraints based on control barrier function","volume":"32","author":"Xu","year":"2022","journal-title":"International Journal of Robust and Nonlinear Control"},{"key":"10.1016\/j.neunet.2026.109685_bib0034","series-title":"Advances in neural information processing systems","first-page":"9111","article-title":"Constrained update projection approach to safe policy optimization","volume":"vol. 35","author":"Yang","year":"2022"},{"issue":"6","key":"10.1016\/j.neunet.2026.109685_bib0035","doi-asserted-by":"crossref","first-page":"3316","DOI":"10.1016\/j.jfranklin.2019.12.017","article-title":"Online barrier-actor-critic learning for h\u221e control with full-state constraints and input saturation","volume":"357","author":"Yang","year":"2020","journal-title":"Journal of the Franklin Institute"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0036","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/TNNLS.2023.3326397","article-title":"Optimal control for constrained discrete-time nonlinear systems based on safe reinforcement learning","volume":"36","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109685_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2024.111714","article-title":"Safety reinforcement learning control via transfer learning","volume":"166","author":"Zhang","year":"2024","journal-title":"Automatica"},{"issue":"3","key":"10.1016\/j.neunet.2026.109685_bib0038","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/TAC.2018.2845707","article-title":"Removing the feasibility conditions imposed on tracking control designs for state-constrained strict-feedback systems","volume":"64","author":"Zhao","year":"2018","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/j.neunet.2026.109685_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107249","article-title":"Neural-network-based accelerated safe q-learning for optimal control of discrete-time nonlinear systems with state constraints","volume":"186","author":"Zhao","year":"2025","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.neunet.2026.109685_bib0040","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1109\/TII.2024.3488790","article-title":"Integrated online q-learning design for wastewater treatment processes","volume":"21","author":"Zhao","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"12","key":"10.1016\/j.neunet.2026.109685_bib0041","doi-asserted-by":"crossref","first-page":"2408","DOI":"10.1109\/JAS.2024.124509","article-title":"Safe q-learning for data-driven nonlinear optimal control with asymmetric state constraints","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0042","doi-asserted-by":"crossref","first-page":"36","DOI":"10.23919\/AISE.2026.000003","article-title":"Online learning in a creator economy","volume":"2","author":"Zhu","year":"2026","journal-title":"Artificial Intelligence Science and Engineering"},{"issue":"1","key":"10.1016\/j.neunet.2026.109685_bib0043","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2020","journal-title":"Proceedings of the IEEE"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011408?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011408?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:51:43Z","timestamp":1793605903000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":43,"alternative-id":["S0893608026011408"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109685","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Transfer learning-based safe Q-learning for discrete-time nonlinear systems with asymmetric state constraints","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109685","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109685"}}