{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:54:49Z","timestamp":1764960889399,"version":"3.46.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018527","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030204"],"award-info":[{"award-number":["XDA27030204"]}],"id":[{"id":"10.13039\/501100018527","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322316","62073323"],"award-info":[{"award-number":["62322316","62073323"]}],"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","20230484435"],"award-info":[{"award-number":["20220484077","20230484435"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3423417","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T14:19:22Z","timestamp":1722521962000},"page":"9621-9635","source":"Crossref","is-referenced-by-count":1,"title":["A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5120-2046","authenticated-orcid":false,"given":"Qingxu","family":"Fu","sequence":"first","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\/0000-0003-3268-9482","authenticated-orcid":false,"given":"Jianqiang","family":"Yi","sequence":"additional","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"}]},{"given":"Wanmai","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref2","article-title":"Episodic exploration for deep deterministic policies: An application to StarCraft micromanagement tasks","author":"Usunier","year":"2016","journal-title":"arXiv:1609.02993"},{"key":"ref3","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv:1706.02275"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8794134"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78743-1_2"},{"key":"ref6","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"Agarwal","year":"2019","journal-title":"arXiv:1906.01202"},{"key":"ref7","article-title":"Emergent tool use from multi-agent autocurricula","author":"Baker","year":"2019","journal-title":"arXiv:1909.07528"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207657"},{"key":"ref11","first-page":"1","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chenghao"},{"key":"ref12","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref13","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref14","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Iqbal"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891991"},{"issue":"129","key":"ref17","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (MARL) using mean field control (MFC)","volume":"23","author":"Mondal","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2010.5584466"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmaa.2005.08.094"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2017.7978499"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref26","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12597-012-0077-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/h0025589"},{"key":"ref31","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","author":"Hu","year":"2021","journal-title":"arXiv:2102.03479"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21165"},{"key":"ref33","article-title":"Stock prices as Janardan Galton Watson process","author":"Saeb","year":"2022","journal-title":"arXiv:2208.08496"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010007108196"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11893011_89"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2007.07.043"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref39","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172572"},{"key":"ref41","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020","journal-title":"arXiv:2008.01062"},{"key":"ref42","article-title":"QTRAN++: Improved value transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2020","journal-title":"arXiv:2006.12010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3146858"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3329530"},{"key":"ref45","article-title":"Graph convolutional value decomposition in multi-agent reinforcement learning","author":"Naderializadeh","year":"2020","journal-title":"arXiv:2010.04740"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309608"},{"key":"ref47","article-title":"Learning attentional communication for multi-agent cooperation","author":"Jiang","year":"2018","journal-title":"arXiv:1805.07733"},{"key":"ref48","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Das"},{"key":"ref49","first-page":"2244","article-title":"Learning multi-agent communication with backpropagation","volume-title":"Proc. Advance Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref50","article-title":"R-MADDPG for partially observable environments and limited communication","author":"Wang","year":"2020","journal-title":"arXiv:2002.06684"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089834"},{"key":"ref52","first-page":"1278","article-title":"Hierarchical multi-agent reinforcement learning for maritime traffic management","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst.","author":"Singh"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3243557"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3479-9"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236361"},{"key":"ref57","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref58","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan"},{"key":"ref59","article-title":"Influence-based multi-agent exploration","author":"Wang","year":"2019","journal-title":"arXiv:1910.05512"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref61","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2013","journal-title":"arXiv:1312.6120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1201\/9780429029608"},{"key":"ref63","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","volume":"34","author":"Zheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236361"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2019.8929168"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10620308.pdf?arnumber=10620308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:43Z","timestamp":1764959983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3423417","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}