{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:09Z","timestamp":1775578389415,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61976115"],"award-info":[{"award-number":["61976115"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61732006"],"award-info":[{"award-number":["61732006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004193","name":"AI+ Project of the Nanjing University of Aeronautics and Astronautics","doi-asserted-by":"publisher","award":["XZA20005"],"award-info":[{"award-number":["XZA20005"]}],"id":[{"id":"10.13039\/501100004193","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004193","name":"AI+ Project of the Nanjing University of Aeronautics and Astronautics","doi-asserted-by":"publisher","award":["56XZA18009"],"award-info":[{"award-number":["56XZA18009"]}],"id":[{"id":"10.13039\/501100004193","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project","award":["315025305"],"award-info":[{"award-number":["315025305"]}]},{"name":"Graduate Innovation Foundation of NUAA","award":["Kfjj20191608"],"award-info":[{"award-number":["Kfjj20191608"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tnnls.2021.3089493","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:16:38Z","timestamp":1624914998000},"page":"52-63","source":"Crossref","is-referenced-by-count":26,"title":["SMIX(\u03bb): Enhancing Centralized Value Functions for Cooperative Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8323-4114","authenticated-orcid":false,"given":"Xinghu","family":"Yao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1676-5177","authenticated-orcid":false,"given":"Chao","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0502-7486","authenticated-orcid":false,"given":"Yuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2683-8667","authenticated-orcid":false,"given":"Xiaoyang","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s150510026"},{"key":"ref2","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. Learn., Inference Control Multi-Agent Syst. Workshop NIPS","author":"Van der Pol"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2922174"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2403394"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2598355"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2673020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2651402"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref9","first-page":"6846","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2010-0206"},{"key":"ref11","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref14","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag"},{"key":"ref15","first-page":"10329","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref16","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref17","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref20","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Munos"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"ref22","article-title":"Understanding multi-step deep reinforcement learning: A systematic study of the DQN target","author":"Hernandez-Garcia","year":"2019","journal-title":"arXiv:1901.07510"},{"key":"ref23","first-page":"3599","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref24","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"Papoudakis","year":"2019","journal-title":"arXiv:1906.04737"},{"key":"ref25","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tesauro"},{"key":"ref26","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lauer"},{"key":"ref27","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"1879","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Foerster"},{"key":"ref29","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Samvelyan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref31","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume-title":"Proc. 6th Conf. Theor. Aspects Rationality Knowl. (TARK)","author":"Boutilier"},{"key":"ref32","first-page":"1973","article-title":"A new Q ($\\lambda$\n) with interim forward view and monte carlo equivalence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutton"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"ref34","first-page":"5356","article-title":"Breaking the curse of horizon: Infinite-horizon off-policy estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref35","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Deep Learn. Represent. Learn. Workshop (NIPS)","author":"Chung"},{"key":"ref36","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ha"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref38","first-page":"7613","article-title":"Maven: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_21"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10007736\/09466372.pdf?arnumber=9466372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:06:32Z","timestamp":1705017992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9466372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3089493","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}