{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:32:45Z","timestamp":1766269965924,"version":"3.48.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA27030204"],"award-info":[{"award-number":["XDA27030204"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322316"],"award-info":[{"award-number":["62322316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20220484077"],"award-info":[{"award-number":["20220484077"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484435"],"award-info":[{"award-number":["20230484435"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcds.2025.3570497","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:46:42Z","timestamp":1747403202000},"page":"1520-1535","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Actor\u2013Critic for Physically Heterogeneous Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2570-2287","authenticated-orcid":false,"given":"Tianyi","family":"Hu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4841-4048","authenticated-orcid":false,"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7943-8336","authenticated-orcid":false,"given":"Xiaolin","family":"Ai","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0312-5728","authenticated-orcid":false,"given":"Tenghai","family":"Qiu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-8540","authenticated-orcid":false,"given":"Yanyan","family":"Liang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Taipa, Macau"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-9482","authenticated-orcid":false,"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3404061"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3345735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3303848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6858632"},{"key":"ref9","first-page":"1485","article-title":"Heterogeneous multi-robot reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Bettini","year":"2023"},{"key":"ref10","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref11","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref12","article-title":"Rode: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Represent. Learn.","author":"Wang","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxac121"},{"key":"ref14","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"834","article-title":"Measuring policy distance for multi-agent reinforcement learning","volume-title":"Proc. Int. Found. Auton. Agents Multiagent Syst.","author":"Hu","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5753\/eniac.2020.12161"},{"article-title":"Heterogeneous graph attention networks for learning diverse communication","year":"2021","author":"Seraj","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01415-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04866-0"},{"article-title":"Heterogeneous multi-agent reinforcement learning for unknown environment mapping","year":"2020","author":"Wakilpoor","key":"ref20"},{"article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","year":"2020","author":"Terry","key":"ref21"},{"key":"ref22","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"article-title":"The StarCraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref23"},{"article-title":"Unreal-map: Unreal-engine-based general platform for multi-agent reinforcement learning","year":"2025","author":"Hu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.037"},{"key":"ref27","article-title":"Maximum entropy heterogeneous-agent reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent","author":"Liu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref29","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rashid","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007219"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/545056.545078"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref33","first-page":"2945","article-title":"Fully decentralized policies for multi-agent systems: An information theoretic approach","volume":"30","author":"Dobbe","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283339"},{"key":"ref35","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"33","author":"Zhou","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref36","first-page":"29142","article-title":"Towards understanding cooperative multi-agent q-learning with value factorization","volume":"34","author":"Wang","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref37","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"Proc. Int. Found. Auton. Agents Multiagent Syst."},{"issue":"1","key":"ref38","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":"ref39","article-title":"QPLEX: Duplex dueling multi-agent q-learning","author":"Wang","year":"2021","journal-title":"Proc. Int. Conf. Represent. Learn."},{"key":"ref40","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref42","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","year":"2019","author":"Ackermann","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"Chung","key":"ref45"},{"key":"ref46","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin","year":"2015"},{"key":"ref47","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"Proc. Int. Conf. Represent. Learn."},{"key":"ref48","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2016","journal-title":"Proc. Int. Conf. Learn. Represent."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11288412\/11006503.pdf?arnumber=11006503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:33:14Z","timestamp":1765909994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11006503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3570497","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}