{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:04:03Z","timestamp":1775837043349,"version":"3.50.1"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1710005"],"award-info":[{"award-number":["2020YFB1710005"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Reliability Engineering & System Safety"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.ress.2026.112467","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:07:13Z","timestamp":1772122033000},"page":"112467","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Optimization of continuous condition-based maintenance for multi-component equipment clusters based on multi-agent incremental reinforcement learning"],"prefix":"10.1016","volume":"272","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3897-8406","authenticated-orcid":false,"given":"Shiao","family":"Yao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-7741","authenticated-orcid":false,"given":"Daofang","family":"Chang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5404-5154","authenticated-orcid":false,"given":"Haitao","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0602-2983","authenticated-orcid":false,"given":"Congming","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8107-170X","authenticated-orcid":false,"given":"Jingsen","family":"Huang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.ress.2026.112467_bib0001","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.ejor.2017.02.044","article-title":"Condition-based maintenance policies for systems with multiple dependent components: a review","volume":"261","author":"Olde Keizer","year":"2017","journal-title":"Eur J Oper Res"},{"key":"10.1016\/j.ress.2026.112467_bib0002","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ress.2016.08.009","article-title":"A review on condition-based maintenance optimization models for stochastically deteriorating system","volume":"157","author":"Alaswad","year":"2017","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2024.109603","article-title":"A dynamic maintenance policy for degradation system by state monitoring and deep reinforcement learning","volume":"119","author":"Xu","year":"2024","journal-title":"Comput Electr Eng"},{"issue":"1","key":"10.1016\/j.ress.2026.112467_bib0004","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.cie.2012.02.002","article-title":"An overview of time-based and condition-based maintenance in industrial application","volume":"63","author":"Ahmad","year":"2012","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118413","article-title":"Predictive maintenance for critical infrastructure","volume":"210","author":"Gorenstein","year":"2022","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113701","article-title":"Deep reinforcement learning based preventive maintenance policy for serial production lines","volume":"160","author":"Huang","year":"2020","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114399","article-title":"A reinforcement learning-based algorithm for the aircraft maintenance routing problem","volume":"169","author":"Ruan","year":"2021","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0008","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.compind.2016.07.003","article-title":"A framework for effective management of condition based maintenance programs in the context of industrial development of e-maintenance strategies","volume":"82","author":"Guill\u00e9n","year":"2016","journal-title":"Comput Ind"},{"key":"10.1016\/j.ress.2026.112467_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114598","article-title":"Predictive maintenance system for production lines in manufacturing: a machine learning approach using IoT data in real-time","volume":"173","author":"Ayvaz","year":"2021","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2020.103298","article-title":"Machine learning and reasoning for predictive maintenance in industry 4.0: current status and challenges","volume":"123","author":"Dalzochio","year":"2020","journal-title":"Comput Ind"},{"key":"10.1016\/j.ress.2026.112467_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2021.103531","article-title":"Maintenance concepts evolution: a comparative review towards advanced maintenance conceptualization","volume":"133","author":"Roda","year":"2021","journal-title":"Comput Ind"},{"key":"10.1016\/j.ress.2026.112467_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106889","article-title":"Predictive maintenance in the industry 4.0: a systematic literature review","volume":"150","author":"Zonta","year":"2020","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0013","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.promfg.2020.04.032","article-title":"Artificial intelligence for predictive maintenance in the railcar learning factories","volume":"45","author":"Daniyan","year":"2020","journal-title":"Procedia Manuf"},{"key":"10.1016\/j.ress.2026.112467_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110401","article-title":"Reinforcement learning in reliability and maintenance optimization: a tutorial","volume":"251","author":"Zhang","year":"2024","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2020.106955","article-title":"Integrated optimization of maintenance interventions and spare part selection for a partially observable multi-component system","volume":"200","author":"Karaba\u011f","year":"2020","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.108112","article-title":"A gamma process based model for systems subject to multiple dependent competing failure processes under markovian environments","volume":"217","author":"Wu","year":"2022","journal-title":"Reliab Eng Syst Saf"},{"issue":"23","key":"10.1016\/j.ress.2026.112467_bib0017","doi-asserted-by":"crossref","first-page":"7160","DOI":"10.1080\/00207543.2018.1436789","article-title":"Selective maintenance scheduling under stochastic maintenance quality with multiple maintenance actions","volume":"56","author":"Duan","year":"2018","journal-title":"Int J Prod Res"},{"key":"10.1016\/j.ress.2026.112467_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110127","article-title":"Knowledge transfer for adaptive maintenance policy optimization in engineering fleets based on meta-reinforcement learning","volume":"247","author":"Cheng","year":"2024","journal-title":"Reliab Eng Syst Saf"},{"issue":"8","key":"10.1016\/j.ress.2026.112467_bib0019","doi-asserted-by":"crossref","first-page":"5362","DOI":"10.1109\/TPAMI.2024.3367329","article-title":"A comprehensive survey of continual learning: theory, method and application","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.ress.2026.112467_bib0020","first-page":"1","article-title":"Multi-incremental learning-based predictive modeling for unknown distributed parameter systems under larger working region","volume":"74","author":"Wang","year":"2025","journal-title":"IEEE Trans Instrum Meas"},{"issue":"7","key":"10.1016\/j.ress.2026.112467_bib0021","doi-asserted-by":"crossref","first-page":"5245","DOI":"10.1109\/TII.2025.3552705","article-title":"Sparse information completion-based incremental learning for modeling of complex distributed parameter systems","volume":"21","author":"Wang","year":"2025","journal-title":"IEEE Trans Ind Inf"},{"issue":"C","key":"10.1016\/j.ress.2026.112467_bib0022","article-title":"Spatiotemporal incremental learning with three-dimensional fuzzy fusion for thermal processes modeling under sparse sensing","volume":"325","author":"Wang","year":"2026","journal-title":"Knowl-Based Syst"},{"key":"10.1016\/j.ress.2026.112467_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2023.109597","article-title":"Optimal maintenance policy for systems with environment-modulated degradation and random shocks considering imperfect maintenance","volume":"240","author":"Mai","year":"2023","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110072","article-title":"Condition-based maintenance policy for systems under dynamic environment","volume":"246","author":"Luo","year":"2024","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0025","doi-asserted-by":"crossref","first-page":"7967","DOI":"10.1007\/s10994-024-06559-2","article-title":"Pomdp inference and robust solution via deep reinforcement learning: an application to railway optimal maintenance","volume":"113","author":"Arcieri","year":"2024","journal-title":"Mach Learn"},{"issue":"11-12","key":"10.1016\/j.ress.2026.112467_bib0026","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1080\/15732479.2025.2559150","article-title":"District-level bridge networks management with multi-agent reinforcement learning: from theory to real-world application","volume":"21","author":"Bhattacharya","year":"2025","journal-title":"Struct Infrastruct Eng"},{"issue":"9","key":"10.1016\/j.ress.2026.112467_bib0027","doi-asserted-by":"crossref","DOI":"10.1061\/JBENF2.BEENG-6159","article-title":"Sustainable life-cycle maintenance policymaking for network-level deteriorating bridges with a convolutional autoencoder\u2013structured reinforcement learning agent","volume":"28","author":"Lei","year":"2023","journal-title":"J Bridge Eng"},{"issue":"6","key":"10.1016\/j.ress.2026.112467_bib0028","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CP.1943-5487.0000991","article-title":"A decision-making framework for load rating planning of aging bridges using deep reinforcement learning","volume":"35","author":"Cheng","year":"2021","journal-title":"J Comput Civil Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2021.107321","article-title":"Reinforcement learning with gaussian processes for condition-based maintenance","volume":"158","author":"Peng","year":"2021","journal-title":"Comput Ind Eng"},{"issue":"12","key":"10.1016\/j.ress.2026.112467_bib0030","doi-asserted-by":"crossref","first-page":"8254","DOI":"10.1109\/TII.2021.3066257","article-title":"An intelligent preventive maintenance method based on reinforcement learning for battery energy storage systems","volume":"17","author":"Wu","year":"2021","journal-title":"IEEE Trans Ind Inf"},{"key":"10.1016\/j.ress.2026.112467_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2024.124431","article-title":"A deep reinforcement learning ensemble for maintenance scheduling in offshore wind farms","volume":"377","author":"Lee","year":"2025","journal-title":"Appl Energy"},{"key":"10.1016\/j.ress.2026.112467_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110477","article-title":"Comparative analysis of offshore wind turbine blade maintenance: RL-based and classical strategies for sustainable approach","volume":"253","author":"Hendradewa","year":"2025","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.107056","article-title":"Reinforcement learning-driven maintenance strategy: a novel solution for long-term aircraft maintenance decision optimization","volume":"153","author":"Hu","year":"2021","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0034","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1016\/j.jmsy.2023.05.005","article-title":"A multi-agent convolution deep reinforcement learning network for aeroengine fleet maintenance strategy optimization","volume":"68","author":"Xia","year":"2023","journal-title":"J Manuf Syst"},{"key":"10.1016\/j.ress.2026.112467_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123358","article-title":"Collaborative-sequential optimization for aero-engine maintenance based on multi-agent reinforcement learning","volume":"247","author":"Wei","year":"2024","journal-title":"Expert Syst Appl"},{"issue":"9","key":"10.1016\/j.ress.2026.112467_bib0036","doi-asserted-by":"crossref","first-page":"5338","DOI":"10.1109\/LRA.2023.3294717","article-title":"Integrating robot assignment and maintenance management: a multi-agent reinforcement learning approach for holistic control","volume":"8","author":"Bhatta","year":"2023","journal-title":"IEEE Rob Autom Lett"},{"key":"10.1016\/j.ress.2026.112467_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2023.102594","article-title":"An integrated control strategy for simultaneous robot assignment, tool change and preventive maintenance scheduling using heterogeneous graph neural network","volume":"84","author":"Bhatta","year":"2023","journal-title":"Robot Comput Integr Manuf"},{"issue":"1","key":"10.1016\/j.ress.2026.112467_bib0038","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1109\/TR.2020.3044596","article-title":"A deep reinforcement learning approach to dynamic loading strategy of repairable multistate systems","volume":"71","author":"Chen","year":"2022","journal-title":"IEEE Trans Reliab"},{"key":"10.1016\/j.ress.2026.112467_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.108078","article-title":"Maintenance optimisation of multicomponent systems using hierarchical coordinated reinforcement learning","volume":"217","author":"Zhou","year":"2022","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2019.04.036","article-title":"Managing engineering systems with large state and action spaces through deep reinforcement learning","volume":"191","author":"Andriotis","year":"2019","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.107551","article-title":"Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints","volume":"212","author":"Andriotis","year":"2021","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2022.108643","article-title":"Condition-based maintenance strategy for redundant systems with arbitrary structures using improved reinforcement learning","volume":"225","author":"Yang","year":"2022","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0043","doi-asserted-by":"crossref","first-page":"15549","DOI":"10.1007\/s00521-023-08542-9","article-title":"A deep reinforcement learning approach for maintenance planning of multi-component systems with complex structure","volume":"35","author":"Chen","year":"2023","journal-title":"Neural Comput Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.111478","article-title":"Resilience-based post disaster recovery optimization for infrastructure system via deep reinforcement learning","volume":"265","author":"Liang","year":"2026","journal-title":"Reliab Eng Syst Saf"},{"issue":"4","key":"10.1016\/j.ress.2026.112467_bib0045","doi-asserted-by":"crossref","first-page":"1967","DOI":"10.1109\/TR.2024.3389015","article-title":"Joint multimission selective maintenance and inventory optimization for multicomponent systems considering stochastic dependency","volume":"73","author":"Kong","year":"2024","journal-title":"IEEE Trans Reliab"},{"key":"10.1016\/j.ress.2026.112467_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2023.109628","article-title":"Joint maintenance and spare part ordering from multiple suppliers for multicomponent systems using a deep reinforcement learning algorithm","volume":"241","author":"Zheng","year":"2024","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.110837","article-title":"Condition-based maintenance for redundant systems considering spare inventory with stochastic lead time","volume":"257","author":"Wang","year":"2025","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2023.109144","article-title":"Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning","volume":"235","author":"Morato","year":"2023","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.112467_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116323","article-title":"Deep multi-agent reinforcement learning for multi-level preventive maintenance in manufacturing systems","volume":"192","author":"Su","year":"2022","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.ress.2026.112467_bib0050","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jmsy.2023.08.011","article-title":"Counterfactual-attention multi-agent reinforcement learning for joint condition-based maintenance and production scheduling","volume":"71","author":"Zhang","year":"2023","journal-title":"J Manuf Syst"},{"key":"10.1016\/j.ress.2026.112467_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109631","article-title":"Knowledge-enhanced reinforcement learning for multi-machine integrated production and maintenance scheduling","volume":"185","author":"Hu","year":"2023","journal-title":"Comput Ind Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0052","first-page":"1401","article-title":"Towards continual reinforcement learning: a review and perspectives","volume":"75","author":"Khetarpal","year":"2022","journal-title":"J Artif Intell"},{"key":"10.1016\/j.ress.2026.112467_bib0053","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s10489-020-01786-1","article-title":"Sler: self-generated long-term experience replay for continual reinforcement learning","volume":"51","author":"Li","year":"2021","journal-title":"Appl Intell"},{"key":"10.1016\/j.ress.2026.112467_bib0054","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.neucom.2020.11.050","article-title":"Pseudo-rehearsal: achieving deep reinforcement learning without catastrophic forgetting","volume":"428","author":"Atkinson","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ress.2026.112467_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106056","article-title":"Balanced incremental deep reinforcement learning based on variational autoencoder data augmentation for customer credit scoring","volume":"122","author":"Wang","year":"2023","journal-title":"Eng Appl Artif Intell"},{"issue":"12","key":"10.1016\/j.ress.2026.112467_bib0056","doi-asserted-by":"crossref","first-page":"7744","DOI":"10.1109\/TSMC.2023.3299556","article-title":"Continual reinforcement learning formulation for zero-sum game-based constrained optimal tracking","volume":"53","author":"Farzanegan","year":"2023","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"12","key":"10.1016\/j.ress.2026.112467_bib0057","doi-asserted-by":"crossref","first-page":"9925","DOI":"10.1109\/TNNLS.2022.3162241","article-title":"Catastrophic interference in reinforcement learning: a solution based on context division and knowledge distillation","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"10.1016\/j.ress.2026.112467_bib0058","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1109\/TPAMI.2022.3225310","article-title":"Rectification-based knowledge retention for task incremental learning","volume":"46","author":"Mazumder","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"10.1016\/j.ress.2026.112467_bib0059","doi-asserted-by":"crossref","first-page":"11242","DOI":"10.1109\/LRA.2024.3487484","article-title":"Mitigating catastrophic forgetting in robot continual learning: a guided policy search approach enhanced with memory-aware synapses","volume":"9","author":"Dong","year":"2024","journal-title":"IEEE Rob Autom Lett"},{"issue":"12","key":"10.1016\/j.ress.2026.112467_bib0060","doi-asserted-by":"crossref","first-page":"7509","DOI":"10.1109\/TCYB.2022.3170485","article-title":"A Dirichlet process mixture of robust task models for scalable lifelong reinforcement learning","volume":"53","author":"Wang","year":"2023","journal-title":"IEEE Trans Cybern"},{"issue":"10","key":"10.1016\/j.ress.2026.112467_bib0061","doi-asserted-by":"crossref","first-page":"14739","DOI":"10.1109\/TNNLS.2023.3281473","article-title":"Efficient multitask reinforcement learning without performance loss","volume":"35","author":"Baek","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"10","key":"10.1016\/j.ress.2026.112467_bib0062","doi-asserted-by":"crossref","first-page":"14588","DOI":"10.1109\/TNNLS.2023.3280085","article-title":"Dynamics-adaptive continual reinforcement learning via progressive contextualization","volume":"35","author":"Zhang","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"10.1016\/j.ress.2026.112467_bib0063","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1080\/08982112.2021.1977950","article-title":"Dynamic maintenance model for a repairable multi-component system using deep reinforcement learning","volume":"34","author":"Yousefi","year":"2022","journal-title":"Qual Eng"},{"key":"10.1016\/j.ress.2026.112467_bib0064","series-title":"ICLR 2016","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2016"},{"issue":"13","key":"10.1016\/j.ress.2026.112467_bib0065","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc Natl Acad Sci"}],"container-title":["Reliability Engineering & System Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026002838?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026002838?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T15:34:21Z","timestamp":1775835261000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0951832026002838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":65,"alternative-id":["S0951832026002838"],"URL":"https:\/\/doi.org\/10.1016\/j.ress.2026.112467","relation":{},"ISSN":["0951-8320"],"issn-type":[{"value":"0951-8320","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Optimization of continuous condition-based maintenance for multi-component equipment clusters based on multi-agent incremental reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Reliability Engineering & System Safety","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ress.2026.112467","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":"112467"}}