{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T03:08:37Z","timestamp":1789096117457,"version":"build-2803163510"},"reference-count":35,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["ISA Transactions"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.isatra.2026.07.027","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T23:51:35Z","timestamp":1785455495000},"page":"538-549","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Fuzzy\u2013TD3: A prior-knowledge guided deterministic policy gradient for interpretable control"],"prefix":"10.1016","volume":"177","author":[{"given":"Kainan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linxiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Ban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengkun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbin","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.isatra.2026.07.027_bib0005","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","article-title":"Optimal and autonomous control using reinforcement learning: a survey","volume":"29","author":"Kiumarsi","year":"2017","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0010","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1007\/s10462-021-09997-9","article-title":"Reinforcement learning in robotic applications: a comprehensive survey","volume":"55","author":"Singh","year":"2022","journal-title":"Artif Intell Rev"},{"key":"10.1016\/j.isatra.2026.07.027_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110155","article-title":"Dynamic scheduling mechanism for intelligent workshop with deep reinforcement learning method based on multi-agent system architecture","volume":"191","author":"Gu","year":"2024","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.isatra.2026.07.027_bib0020","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: a brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process Mag"},{"key":"10.1016\/j.isatra.2026.07.027_bib0025","series-title":"International cross-domain conference for machine learning and knowledge extraction","first-page":"77","article-title":"Explainable reinforcement learning: a survey","author":"Puiutta","year":"2020"},{"key":"10.1016\/j.isatra.2026.07.027_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2025.110856","article-title":"Deep reinforcement learning for machine scheduling: methodology, the state-of-the-art, and future directions","author":"Khadivi","year":"2025","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.isatra.2026.07.027_bib0035","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1109\/TSMC.2023.3312411","article-title":"Leveraging reward consistency for interpretable feature discovery in reinforcement learning","volume":"54","author":"Yang","year":"2023","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0040","first-page":"441","article-title":"Fuzzy inference system: short review and design","volume":"6","author":"Sabri","year":"2013","journal-title":"Int. Rev. Autom. Control"},{"key":"10.1016\/j.isatra.2026.07.027_bib0045","doi-asserted-by":"crossref","first-page":"4944","DOI":"10.1109\/TSMC.2019.2944893","article-title":"A survey of belief rule-base expert system","volume":"51","author":"Zhou","year":"2019","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0050","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/91.728456","article-title":"General SISO Takagi-Sugeno fuzzy systems with linear rule consequent are universal approximators","volume":"6","author":"Ying","year":"1998","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0055","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1049\/trit.2018.1007","article-title":"Adaptive PID controller based on Q-learning algorithm","volume":"3","author":"Shi","year":"2018","journal-title":"CAAI Trans Intell Technol"},{"key":"10.1016\/j.isatra.2026.07.027_bib0060","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1109\/TSMCB.2004.825938","article-title":"Online tuning of fuzzy inference systems using dynamic fuzzy Q-learning","volume":"34","author":"Er","year":"2004","journal-title":"IEEE Trans. Syst. Man Cybern. B, Cybern."},{"key":"10.1016\/j.isatra.2026.07.027_bib0065","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.ejcon.2020.03.001","article-title":"A Q-learning predictive control scheme with guaranteed stability","volume":"56","author":"Beckenbach","year":"2020","journal-title":"Eur. J. Control"},{"key":"10.1016\/j.isatra.2026.07.027_bib0070","doi-asserted-by":"crossref","first-page":"9926","DOI":"10.1109\/ACCESS.2021.3050167","article-title":"Optimal tracking current control of switched reluctance motor drives using reinforcement Q-learning scheduling","volume":"9","author":"Alharkan","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.isatra.2026.07.027_bib0075","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.cie.2017.05.026","article-title":"A reinforcement learning approach to parameter estimation in dynamic job shop scheduling","volume":"110","author":"Shahrabi","year":"2017","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.isatra.2026.07.027_bib0080","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1016\/j.isatra.2020.01.016","article-title":"Fuzzy reinforcement learning based intelligent classifier for power transformer faults","volume":"101","author":"Malik","year":"2020","journal-title":"ISA Trans"},{"key":"10.1016\/j.isatra.2026.07.027_bib0085","doi-asserted-by":"crossref","first-page":"5211","DOI":"10.1109\/TFUZZ.2022.3170646","article-title":"Using fuzzy logic to learn abstract policies in large-scale multiagent reinforcement learning","volume":"30","author":"Li","year":"2022","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0090","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.isatra.2024.12.045","article-title":"Fuzzy reinforcement learning based control of linear systems with input saturation","volume":"158","author":"Liu","year":"2025","journal-title":"ISA Trans"},{"key":"10.1016\/j.isatra.2026.07.027_bib0095","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.neucom.2018.11.072","article-title":"Hybrid hierarchical reinforcement learning for online guidance and navigation with partial observability","volume":"331","author":"Zhou","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.isatra.2026.07.027_bib0100","series-title":"International conference on machine learning","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"Gu","year":"2016"},{"key":"10.1016\/j.isatra.2026.07.027_bib0105","series-title":"International conference on machine learning","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"Silver","year":"2014"},{"key":"10.1016\/j.isatra.2026.07.027_bib0110","author":"Lillicrap"},{"key":"10.1016\/j.isatra.2026.07.027_bib0115","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.isatra.2026.07.027_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113087","article-title":"Knowledge guided deep deterministic policy gradient","volume":"311","author":"Qin","year":"2025","journal-title":"Knowl-Based Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0125","doi-asserted-by":"crossref","first-page":"2808","DOI":"10.1016\/j.fss.2010.06.004","article-title":"A neural-fuzzy modelling framework based on granular computing: concepts and applications","volume":"161","author":"Panoutsos","year":"2010","journal-title":"Fuzzy Sets Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0130","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.isatra.2024.03.023","article-title":"Fuzzy-based collective pitch control for wind turbine via deep reinforcement learning","volume":"148","author":"Nabeel","year":"2024","journal-title":"ISA Trans"},{"key":"10.1016\/j.isatra.2026.07.027_bib0135","series-title":"2020 Chinese automation congress (CAC)","first-page":"538","article-title":"Robot confrontation based on genetic fuzzy system guided deep deterministic policy gradient algorithm","author":"Gu","year":"2020"},{"key":"10.1016\/j.isatra.2026.07.027_bib0140","doi-asserted-by":"crossref","DOI":"10.3390\/app152312776","article-title":"Fuzzy-partitioned multi-agent TD3 for photovoltaic maximum power point tracking under partial shading","volume":"15","author":"Ortiz-Mu\u00f1oz","year":"2025","journal-title":"Appl Sci"},{"key":"10.1016\/j.isatra.2026.07.027_bib0145","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.neucom.2019.07.038","article-title":"A fuzzy deterministic policy gradient algorithm for pursuit-evasion differential games","volume":"362","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.isatra.2026.07.027_bib0150","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.neucom.2020.03.063","article-title":"Adaptive neuro-fuzzy PID controller based on twin delayed deep deterministic policy gradient algorithm","volume":"402","author":"Shi","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.isatra.2026.07.027_bib0155","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-026-42615-8","article-title":"A fuzzy-TD3 hybrid reinforcement learning framework for robust trajectory tracking of the mitsubishi RV-2AJ robotic arm","volume":"16","author":"Hazem","year":"2026","journal-title":"Sci Rep"},{"key":"10.1016\/j.isatra.2026.07.027_bib0160","article-title":"Knowledge guided self-evolving fuzzy deep reinforcement learning with dual-adaptive optimization strategy","author":"Zhu","year":"2025","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.isatra.2026.07.027_bib0165","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.isatra.2026.07.027_bib0170","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/TSMC.1985.6313399","article-title":"Fuzzy identification of systems and its applications to modeling and control","author":"Takagi","year":"1985","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"10.1016\/j.isatra.2026.07.027_bib0175","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.robot.2010.09.006","article-title":"Self-learning fuzzy logic controllers for pursuit\u2013evasion differential games","volume":"59","author":"Desouky","year":"2011","journal-title":"Robot Auton Syst"}],"container-title":["ISA Transactions"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0019057826003939?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0019057826003939?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T02:27:30Z","timestamp":1789093650000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0019057826003939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":35,"alternative-id":["S0019057826003939"],"URL":"https:\/\/doi.org\/10.1016\/j.isatra.2026.07.027","relation":{},"ISSN":["0019-0578"],"issn-type":[{"value":"0019-0578","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fuzzy\u2013TD3: A prior-knowledge guided deterministic policy gradient for interpretable control","name":"articletitle","label":"Article Title"},{"value":"ISA Transactions","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.isatra.2026.07.027","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 International Society of Automation. Published by Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}