{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:41:42Z","timestamp":1776775302414,"version":"3.51.2"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133488","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:56:36Z","timestamp":1774972596000},"page":"133488","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Safe multi-agent reinforcement learning based on adversarial strategy and control barrier function feasible set"],"prefix":"10.1016","volume":"683","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-5673","authenticated-orcid":false,"given":"Shihan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minxin","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Lian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangzeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133488_bib0005","series-title":"Reinforcement Learning: an Introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.neucom.2026.133488_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111604","article-title":"Autonomous obstacle avoidance and target tracking of UAV: transformer for observation sequence in reinforcement learning","volume":"290","author":"Jiang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.133488_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131375","article-title":"A holistic power optimization approach for microgrid control based on deep reinforcement learning","volume":"654","author":"Yao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133488_bib0020","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 Netw."},{"key":"10.1016\/j.neucom.2026.133488_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121802","article-title":"Actor-critic-disturbance reinforcement learning algorithm-based fast finite-time stability of multiagent systems","volume":"699","author":"Zhao","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133488_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106952","article-title":"Event-based adaptive fixed-time optimal control for saturated fault-tolerant nonlinear multiagent systems via reinforcement learning algorithm","volume":"183","author":"Yue","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.133488_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110083","article-title":"Deepmag: deep reinforcement learning with multi-agent graphs for flexible job shop scheduling","volume":"259","author":"Zhang","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.133488_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124627","article-title":"Optimizing gate control coordination signal for urban traffic network boundaries using multi-agent deep reinforcement learning","author":"Kang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133488_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131211","article-title":"Search and rescue operations in wildfires using unmanned aerial vehicles: a multi-agent deep reinforcement learning approach","volume":"653","author":"Collignon","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133488_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106281","article-title":"Reinforcement learning compensated coordination control of multiple mobile manipulators for tight cooperation","volume":"123","author":"Xu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133488_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131236","article-title":"A comprehensive survey of multi-agent deep reinforcement learning for wireless spectrum management","volume":"653","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.neucom.2026.133488_bib0060","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: stability and optimality","volume":"36","author":"Mayne","year":"2000","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.133488_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122117","article-title":"Finite-time safe reinforcement learning control of multi-player nonzero-sum game for quadcopter systems","volume":"712","author":"Tan","year":"2025","journal-title":"Inf. Sci."},{"issue":"3","key":"10.1016\/j.neucom.2026.133488_bib0070","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1109\/LRA.2023.3238656","article-title":"Model-free safe reinforcement learning through neural barrier certificate","volume":"8","author":"Yang","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133488_bib0075","article-title":"Heterogeneous optimal formation control of nonlinear multi-agent systems with unknown dynamics by safe reinforcement learning","volume":"460","author":"Golmisheh","year":"2024","journal-title":"Appl. Math. Comput."},{"issue":"5","key":"10.1016\/j.neucom.2026.133488_bib0080","doi-asserted-by":"crossref","first-page":"4346","DOI":"10.1109\/TITS.2023.3330183","article-title":"Safe reinforcement learning-based motion planning for functional mobile robots suffering uncontrollable mobile robots","volume":"25","author":"Cao","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.133488_bib0085","series-title":"Conference on Robot Learning","first-page":"2373","article-title":"Neural graph control barrier functions guided distributed collision-avoidance multi-agent control","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133488_bib0090","series-title":"2023 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)","first-page":"107","article-title":"Online control barrier functions for decentralized multi-agent navigation","author":"Gao","year":"2023"},{"issue":"3","key":"10.1016\/j.neucom.2026.133488_bib0095","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/TAC.2022.3157791","article-title":"Adversarial resilience for sampled-data systems under high-relative-degree safety constraints","volume":"68","author":"Usevitch","year":"2023","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.neucom.2026.133488_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.109960","article-title":"Sufficient conditions for feasibility of optimal control problems using control barrier functions","volume":"135","author":"Xiao","year":"2022","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.133488_bib0105","series-title":"International Conference on Machine Learning","first-page":"25636","article-title":"Reachability constrained reinforcement learning","author":"Yu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133488_bib0110","series-title":"2019 International Conference on Robotics and Automation (ICRA)","first-page":"8550","article-title":"Bridging hamilton-jacobi safety analysis and reinforcement learning","author":"Fisac","year":"2019"},{"key":"10.1016\/j.neucom.2026.133488_bib0115","series-title":"2021 American Control Conference (ACC)","first-page":"3856","article-title":"Safety-critical control using optimal-decay control barrier function with guaranteed point-wise feasibility","author":"Zeng","year":"2021"},{"key":"10.1016\/j.neucom.2026.133488_bib0120","series-title":"2019 18th European Control Conference (ECC)","first-page":"3420","article-title":"Control barrier functions: theory and applications","author":"Ames","year":"2019"},{"issue":"3","key":"10.1016\/j.neucom.2026.133488_bib0125","doi-asserted-by":"crossref","first-page":"2289","DOI":"10.1109\/TRO.2023.3249564","article-title":"Barriernet: differentiable control barrier functions for learning of safe robot control","volume":"39","author":"Xiao","year":"2023","journal-title":"IEEE Trans. Robot."},{"issue":"4","key":"10.1016\/j.neucom.2026.133488_bib0130","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1109\/TCYB.2020.3000264","article-title":"Distributed formation navigation of constrained second-order multiagent systems with collision avoidance and connectivity maintenance","volume":"52","author":"Fu","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"10.1016\/j.neucom.2026.133488_bib0135","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1109\/TCNS.2022.3203928","article-title":"Decentralized robust collision-avoidance for cooperative multirobot systems: a Gaussian process-based control barrier function approach","volume":"10","author":"Hu","year":"2023","journal-title":"IEEE Trans. Control Netw. Syst."},{"key":"10.1016\/j.neucom.2026.133488_bib0140","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.automatica.2016.12.009","article-title":"H\u221e control of linear discrete-time systems: off-policy reinforcement learning","volume":"78","author":"Kiumarsi","year":"2017","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.133488_bib0145","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"10.1016\/j.neucom.2026.133488_bib0150","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","article-title":"Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications","volume":"50","author":"Nguyen","year":"2020","journal-title":"IEEE Trans. Cybern."},{"issue":"8","key":"10.1016\/j.neucom.2026.133488_bib0155","doi-asserted-by":"crossref","first-page":"3861","DOI":"10.1109\/TAC.2016.2638961","article-title":"Control barrier function based quadratic programs for safety critical systems","volume":"62","author":"Ames","year":"2016","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.neucom.2026.133488_bib0160","first-page":"1","article-title":"Discrete-time control barrier function: high-order case and adaptive case","author":"Xiong","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.neucom.2026.133488_bib0165","series-title":"Robot Sci. Syst","article-title":"Discrete control barrier functions for safety-critical control of discrete systems with application to bipedal robot navigation","volume":"vol. 13","author":"Agrawal","year":"2017"},{"key":"10.1016\/j.neucom.2026.133488_bib0170","series-title":"2016 American Control Conference (ACC)","first-page":"322","article-title":"Exponential control barrier functions for enforcing high relative-degree safety-critical constraints","author":"Nguyen","year":"2016"},{"key":"10.1016\/j.neucom.2026.133488_bib0175","series-title":"2020 59th IEEE Conference on Decision and Control (CDC)","first-page":"1896","article-title":"Feasibility-guided learning for constrained optimal control problems","author":"Xiao","year":"2020"},{"key":"10.1016\/j.neucom.2026.133488_bib0180","series-title":"2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS)","first-page":"551","article-title":"Feasibility enhancement of constrained receding horizon control using generalized control barrier function","author":"Ma","year":"2021"},{"key":"10.1016\/j.neucom.2026.133488_bib0185","series-title":"International Conference on Machine Learning","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"Pinto","year":"2017"},{"key":"10.1016\/j.neucom.2026.133488_bib0190","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.automatica.2017.02.009","article-title":"Convergence of iterative learning control for SISO nonrepetitive systems subject to iteration-dependent uncertainties","volume":"79","author":"Meng","year":"2017","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.133488_bib0195","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4213","article-title":"Robust multi-agent reinforcement learning via minimax deep deterministic policy gradient","volume":"vol. 33","author":"Li","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.133488_bib0200","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133488_bib0205","author":"Gu"},{"key":"10.1016\/j.neucom.2026.133488_bib0210","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10639","article-title":"Wcsac: worst-case soft actor critic for safety-constrained reinforcement learning","volume":"vol. 35","author":"Yang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133488_bib0215","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119684","article-title":"Safe reinforcement learning for industrial optimal control: a case study from metallurgical industry","volume":"649","author":"Zheng","year":"2023","journal-title":"Information Sciences"},{"issue":"4","key":"10.1016\/j.neucom.2026.133488_bib0220","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0172395","article-title":"Multiagent cooperation and competition with deep reinforcement learning","volume":"12","author":"Tampuu","year":"2017","journal-title":"PLoS One"},{"issue":"6","key":"10.1016\/j.neucom.2026.133488_bib0225","doi-asserted-by":"crossref","first-page":"3316","DOI":"10.1016\/j.jfranklin.2019.12.017","article-title":"Online barrier-actor-critic learning forH\u221econtrol with full-state constraints and input saturation","volume":"357","author":"Yang","year":"2020","journal-title":"J. Frankl. Inst."},{"issue":"5","key":"10.1016\/j.neucom.2026.133488_bib0230","doi-asserted-by":"crossref","first-page":"4346","DOI":"10.1109\/TITS.2023.3330183","article-title":"Safe reinforcement learning-based motion planning for functional mobile robots suffering uncontrollable mobile robots","volume":"25","author":"Cao","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.133488_bib0235","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Discrete GCBF proximal policy optimization for multi-agent safe optimal control","author":"Zhang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133488_bib0240","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TRO.2025.3530348","article-title":"Gcbf+: a neural graph control barrier function framework for distributed safe multi-agent control","volume":"41","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133488_bib0245","series-title":"2024 43rd Chinese Control Conference (CCC)","first-page":"8292","article-title":"Progressive prioritized experience replay for multi-agent reinforcement learning","author":"Chen","year":"2024"},{"key":"10.1016\/j.neucom.2026.133488_bib0250","author":"Schaul"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008854?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008854?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:47:30Z","timestamp":1776772050000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226008854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0925231226008854"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133488","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Safe multi-agent reinforcement learning based on adversarial strategy and control barrier function feasible set","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133488","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":"133488"}}