{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:49:45Z","timestamp":1783529385095,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0200600"],"award-info":[{"award-number":["2024YFE0200600"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LR23F010005"],"award-info":[{"award-number":["LR23F010005"]}]},{"name":"Information Technology Center and State Key Laboratory of CAD&CG, Zhejiang University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3582909","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:46:14Z","timestamp":1752860774000},"page":"18229-18243","source":"Crossref","is-referenced-by-count":8,"title":["Decentralized Consensus Inference-Based Hierarchical Reinforcement Learning for Multiconstrained UAV Pursuit-Evasion Game"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9205-1853","authenticated-orcid":false,"given":"Yuming","family":"Xiang","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sizhao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Zhejiang Lab, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436973"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.3328"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420960342"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5220\/0010775500003116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013920"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/CCC58697.2023.10240527"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3545083"},{"key":"ref9","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3245124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309608"},{"issue":"1","key":"ref12","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","first-page":"1","article-title":"Efficient multi-agent communication via self-supervised information aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Guan"},{"key":"ref14","first-page":"1","article-title":"Maximum entropy heterogeneous-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Repre.","author":"Liu"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref16","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref17","article-title":"Multi-UAV behavior-based formation with static and dynamic obstacles avoidance via reinforcement learning","author":"Xie","year":"2024","journal-title":"arXiv:2410.18495"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089834"},{"key":"ref20","article-title":"Self-critical alternate learning based semantic broadcast communication","author":"Lu","year":"2023","journal-title":"arXiv:2312.01423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10097-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3054685"},{"key":"ref24","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sukhbaatar"},{"key":"ref25","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref26","first-page":"1","article-title":"Communication in multi-agent reinforcement learning: Intention sharing","volume-title":"Proc. Int. Conf. Learn. Repre.","author":"Kim"},{"key":"ref27","first-page":"1","article-title":"ToM2C: Target-oriented multi-agent communication and cooperation with theory of mind","volume-title":"Proc. Int. Conf. Learn. Repre.","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26385"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-022-01601-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341975"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010740"},{"key":"ref35","first-page":"1","article-title":"Feudal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"5","author":"Dayan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref38","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv:1712.00948"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140074"},{"key":"ref40","article-title":"Modelling, identification and control of a quadrotor helicopter","author":"Bresciani","year":"2008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3298944"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909889"},{"key":"ref43","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Repre.","author":"Schulman"},{"key":"ref44","first-page":"1","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rusu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2023-Spring57618.2023.10199811"},{"key":"ref48","article-title":"Precise payload delivery via unmanned aerial vehicles: An approach using object detection algorithms","author":"Vadduri","year":"2023","journal-title":"arXiv:2310.06329"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS49812.2020.9134922"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00879-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3379508"},{"key":"ref53","article-title":"Robust deep reinforcement learning through adversarial attacks and training: A survey","author":"Schott","year":"2024","journal-title":"arXiv:2403.00420"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26388"},{"key":"ref55","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sutton"},{"key":"ref56","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11084848.pdf?arnumber=11084848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:44Z","timestamp":1759945124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3582909","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}