{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T10:35:17Z","timestamp":1773484517104,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["2022YFA1004701"],"award-info":[{"award-number":["2022YFA1004701"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72271187"],"award-info":[{"award-number":["72271187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373283"],"award-info":[{"award-number":["62373283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tai.2025.3566069","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T13:56:45Z","timestamp":1746626205000},"page":"76-90","source":"Crossref","is-referenced-by-count":2,"title":["A Hierarchical Deep Reinforcement Learning Strategy for Collective Pursuit-Evasion Game With Partial Observations"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5528-8748","authenticated-orcid":false,"given":"Xiaoxiao","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2494-1505","authenticated-orcid":false,"given":"Peng","family":"Yi","sequence":"additional","affiliation":[{"name":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9505-8739","authenticated-orcid":false,"given":"Yiguang","family":"Hong","sequence":"additional","affiliation":[{"name":"Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2023.3235873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3366871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300794"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2002.804040"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2024.3393118"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3120700"},{"key":"ref7","volume-title":"Differential Games: A Mathematical Theory With Applications to Warfare and Pursuit, Control and Optimization.","author":"Isaacs","year":"1999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1965.1098197"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/math11234869"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.34133\/research.0246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3329693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17452-0_6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/12\/5\/053013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3003840"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127701"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO54168.2021.9739257"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.09.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3311428"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3139138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.141"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01336-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992967"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235202"},{"key":"ref28","first-page":"1","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref29","first-page":"118","article-title":"The MAXQ method for hierarchical reinforcement learning","volume":"98","author":"Dietterich","year":"1998","journal-title":"Proc. ICML"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3222143"},{"issue":"178","key":"ref32","first-page":"1","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":"ref33","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref34","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.,","author":"Fujimoto","year":"2018"},{"key":"ref35","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref36","first-page":"15032","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"Terry","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref37","article-title":"Solving Rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2022.100476"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3233853"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s13235-019-00319-x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1201\/b13169"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10708"},{"key":"ref47","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019"},{"key":"ref48","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020"},{"key":"ref49","article-title":"MASAC: A multi-agent soft-actor-critic implementation for PettingZoo","author":"Felten","year":"2023"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11329125\/10990178.pdf?arnumber=10990178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:38:43Z","timestamp":1767724723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10990178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":49,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3566069","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}