{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:15:39Z","timestamp":1780668939172,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017548","name":"National Defense Science and Technology Innovation Fund of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017548","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013061","name":"Jilin Scientific and Technological Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013061","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.aei.2026.104724","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:09:39Z","timestamp":1777586979000},"page":"104724","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Cooperative pursuit of underwater dynamic targets: a heterogeneous graph attention network-based multi-agent reinforcement learning approach"],"prefix":"10.1016","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0196-1810","authenticated-orcid":false,"given":"Zhe","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanli","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlong","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.aei.2026.104724_b0005","doi-asserted-by":"crossref","first-page":"2837","DOI":"10.1109\/TASE.2022.3151607","article-title":"Scalable autonomous separation assurance with heterogeneous multi-agent reinforcement learning","volume":"19","author":"Brittain","year":"2022","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104724_b0010","series-title":"In 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13695","article-title":"Transformer-based multi-agent reinforcement learning for generalization of heterogeneous multi-robot cooperation","author":"Cai","year":"2024"},{"issue":"6","key":"10.1016\/j.aei.2026.104724_b0015","doi-asserted-by":"crossref","first-page":"5173","DOI":"10.1109\/TMC.2025.3530438","article-title":"AAV swarm cooperative search based on scalable multiagent deep reinforcement learning with digital twin-enabled sim-to-real transfer","volume":"24","author":"Cao","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"7","key":"10.1016\/j.aei.2026.104724_b0020","doi-asserted-by":"crossref","first-page":"9693","DOI":"10.1109\/TITS.2025.3562213","article-title":"Complete coverage search for multiple autonomous underwater vehicles based on neuronal activity reassignment","volume":"26","author":"Cao","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"10.1016\/j.aei.2026.104724_b0025","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/s11633-024-1512-6","article-title":"Target search and navigation in heterogeneous robot systems with deep reinforcement learning","volume":"22","author":"Chen","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.aei.2026.104724_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124906","article-title":"USV formation navigation decision-making through hybrid deep reinforcement learning using self-attention mechanism","volume":"256","author":"Cui","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10.1016\/j.aei.2026.104724_b0035","doi-asserted-by":"crossref","first-page":"18872","DOI":"10.1109\/TITS.2024.3417698","article-title":"Hierarchical heterogeneous multi-agent cross-domain search method based on deep reinforcement learning","volume":"25","author":"Dong","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"10","key":"10.1016\/j.aei.2026.104724_b0040","doi-asserted-by":"crossref","first-page":"6851","DOI":"10.1109\/TNNLS.2022.3215774","article-title":"Multiagent reinforcement learning with heterogeneous graph attention network","volume":"34","author":"Du","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"10","key":"10.1016\/j.aei.2026.104724_b0045","doi-asserted-by":"crossref","first-page":"9870","DOI":"10.1109\/JIOT.2020.2994909","article-title":"Value-based hierarchical information collection for AUV-enabled internet of Underwater things","volume":"7","author":"Duan","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.aei.2026.104724_b0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130716","article-title":"Heterogeneous multi-agent reinforcement learning for zero-shot scalable collaboration","volume":"648","author":"Guo","year":"2025","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.aei.2026.104724_b0055","doi-asserted-by":"crossref","first-page":"6049","DOI":"10.1109\/TITS.2023.3341034","article-title":"Distributional soft actor-critic-based multi-AUV cooperative pursuit for maritime security protection","volume":"25","author":"Hou","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.aei.2026.104724_b0060","doi-asserted-by":"crossref","first-page":"12768","DOI":"10.1109\/JIOT.2023.3336055","article-title":"Underwater Searching and Multiround Data Collection via AUV Swarms: an Energy-Efficient AoI-Aware MAPPO Approach","volume":"11","author":"Jiang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.aei.2026.104724_b0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.118498","article-title":"Adaptive meta-reinforcement learning for AUVs 3D guidance and control under unknown ocean currents","volume":"309","author":"Jiang","year":"2024","journal-title":"Ocean Eng."},{"key":"10.1016\/j.aei.2026.104724_b0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127856","article-title":"Heterogeneous multi-agent reinforcement learning based on modularized policy network","volume":"284","author":"Kim","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.aei.2026.104724_b0075","series-title":"In 2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"3289","article-title":"Multi-target pursuit by a decentralized heterogeneous UAV swarm using deep multi-agent reinforcement learning","author":"Kouzeghar","year":"2023"},{"issue":"11","key":"10.1016\/j.aei.2026.104724_b0080","doi-asserted-by":"crossref","first-page":"6545","DOI":"10.1109\/TCYB.2024.3440333","article-title":"Reinforcement learning for synchronization of heterogeneous multiagent systems by improved Q-functions","volume":"54","author":"Li","year":"2024","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.aei.2026.104724_b0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.119432","article-title":"Motion control of autonomous underwater vehicle based on physics-informed offline reinforcement learning","volume":"313","author":"Li","year":"2024","journal-title":"Ocean Eng."},{"key":"10.1016\/j.aei.2026.104724_b0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112124","article-title":"Efficient multi-agent cooperation: Scalable reinforcement learning with heterogeneous graph networks and limited communication","volume":"300","author":"Li","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"3","key":"10.1016\/j.aei.2026.104724_b0095","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1109\/MWC.001.1900387","article-title":"An SDN architecture for AUV-based underwater wireless networks to enable cooperative underwater search","volume":"27","author":"Lin","year":"2020","journal-title":"IEEE Wirel. Commun."},{"key":"10.1016\/j.aei.2026.104724_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125609","article-title":"A high-effective swarm intelligence-based multi-robot cooperation method for target searching in unknown hazardous environments","volume":"262","author":"Lin","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.aei.2026.104724_b0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113377","article-title":"Human attention guided multiagent hierarchical reinforcement learning for heterogeneous agents","volume":"316","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.aei.2026.104724_b0110","unstructured":"Liu, J. R., Zhong, Y. F., Hu, S. Y., Fu, H. B., Fu, Q., Chang, X. J., & Yang, Y. D. (2023). Maximum Entropy Heterogeneous-Agent Reinforcement Learning. arXiv preprint arXiv: 2306.10715v6. Doi:10.48550\/arXiv.2306.10715."},{"issue":"05","key":"10.1016\/j.aei.2026.104724_b0115","doi-asserted-by":"crossref","first-page":"7211","DOI":"10.1609\/aaai.v34i05.6211","article-title":"Multi-agent game abstraction via graph attention neural network","volume":"34","author":"Liu","year":"2020","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.aei.2026.104724_b0120","doi-asserted-by":"crossref","first-page":"14332","DOI":"10.1109\/TASE.2025.3560757","article-title":"Observer-based multi-agent reinforcement learning for pursuit-evasion game with multiple unknown uncertainties","volume":"22","author":"Liu","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"3","key":"10.1016\/j.aei.2026.104724_b0125","doi-asserted-by":"crossref","first-page":"4639","DOI":"10.1109\/TNNLS.2024.3362969","article-title":"Hierarchical reinforcement learning for UAV-PE game with alternative delay update method","volume":"36","author":"Ma","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"7","key":"10.1016\/j.aei.2026.104724_b0130","doi-asserted-by":"crossref","first-page":"9554","DOI":"10.1109\/TITS.2022.3146300","article-title":"Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network","volume":"23","author":"Mo","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"10.1016\/j.aei.2026.104724_b0135","doi-asserted-by":"crossref","first-page":"6881","DOI":"10.1109\/TCYB.2024.3453892","article-title":"Enhancing collaboration in heterogeneous multiagent systems through communication complementary graph","volume":"54","author":"Peng","year":"2024","journal-title":"IEEE Trans. Cybern."},{"issue":"11","key":"10.1016\/j.aei.2026.104724_b0140","doi-asserted-by":"crossref","first-page":"8235","DOI":"10.1109\/TNNLS.2022.3146858","article-title":"Attention enhanced reinforcement learning for multi agent cooperation","volume":"34","author":"Pu","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.aei.2026.104724_b0145","doi-asserted-by":"crossref","first-page":"3833","DOI":"10.1109\/TRO.2024.3431829","article-title":"Heterogeneous policy networks for composite robot team communication and coordination","volume":"40","author":"Seraj","year":"2024","journal-title":"IEEE Trans. Rob."},{"key":"10.1016\/j.aei.2026.104724_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.102942","article-title":"Multi-agent reinforcement learning with weak ties","volume":"118","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"issue":"9","key":"10.1016\/j.aei.2026.104724_b0155","doi-asserted-by":"crossref","first-page":"8271","DOI":"10.1109\/JIOT.2022.3230916","article-title":"Task Scheduling for distributed AUV Network Target Hunting and Searching: an Energy-Efficient AoI-Aware DMAPPO Approach","volume":"10","author":"Wang","year":"2023","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"10.1016\/j.aei.2026.104724_b0160","doi-asserted-by":"crossref","first-page":"6782","DOI":"10.1109\/TVT.2020.2991983","article-title":"Cooperative path planning for heterogeneous unmanned vehicles in a search-and-track mission aiming at an underwater target","volume":"69","author":"Wu","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.aei.2026.104724_b0165","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1109\/LRA.2023.3328448","article-title":"Heterogeneous multi-robot cooperation with asynchronous multi-agent reinforcement learning","volume":"9","author":"Zhang","year":"2024","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"5","key":"10.1016\/j.aei.2026.104724_b0170","doi-asserted-by":"crossref","first-page":"9142","DOI":"10.1109\/JIOT.2023.3322197","article-title":"Hunting task allocation for heterogeneous multi-AUV formation target hunting in IoUT: a game theoretic approach","volume":"11","author":"Zhang","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.aei.2026.104724_b0175","doi-asserted-by":"crossref","first-page":"10958","DOI":"10.1109\/JIOT.2024.3514632","article-title":"Collaborative hunting method of multi-AUV in 3-D IoUT: Searching, tracking, and encirclement keeping","volume":"12","author":"Zhang","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"10","key":"10.1016\/j.aei.2026.104724_b0180","doi-asserted-by":"crossref","first-page":"7900","DOI":"10.1109\/TNNLS.2022.3146976","article-title":"Game of drones: Multi-UAV pursuit-evasion game with online motion planning by deep reinforcement learning","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"32","key":"10.1016\/j.aei.2026.104724_b0185","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"10.1016\/j.aei.2026.104724_b0190","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.1109\/TITS.2024.3509954","article-title":"Edge-enhanced heterogeneous graph transformer with priority-based feature aggregation for multi-agent trajectory prediction","volume":"26","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"10.1016\/j.aei.2026.104724_b0195","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-023-3906-3","article-title":"Joint UAV trajectory and communication design with heterogeneous multi-agent reinforcement learning","volume":"67","author":"Zhou","year":"2024","journal-title":"SCIENCE CHINA Inf. Sci."}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004167?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004167?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:43:12Z","timestamp":1780666992000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626004167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":39,"alternative-id":["S1474034626004167"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104724","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cooperative pursuit of underwater dynamic targets: a heterogeneous graph attention network-based multi-agent reinforcement learning approach","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104724","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":"104724"}}