{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:25:41Z","timestamp":1770963941491,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4303805"],"award-info":[{"award-number":["2024YFB4303805"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Projects in Jiangsu Province","award":["BE2021001-2"],"award-info":[{"award-number":["BE2021001-2"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476121"],"award-info":[{"award-number":["62476121"]}],"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":["12201619"],"award-info":[{"award-number":["12201619"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2025.3641970","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:36:00Z","timestamp":1765305360000},"page":"3967-3983","source":"Crossref","is-referenced-by-count":0,"title":["Shapley Meets DCOP: A Unified Structural Credit Assignment for Multiagent Planning and Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9080-4971","authenticated-orcid":false,"given":"Wanyuan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6089-7970","authenticated-orcid":false,"given":"Qian","family":"Che","sequence":"additional","affiliation":[{"name":"Jiangsu Police College, Nanjing, China"}]},{"given":"Chunyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2984-734X","authenticated-orcid":false,"given":"Youzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation, New Territories, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8249-1725","authenticated-orcid":false,"given":"Jiuchuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nanjing University of Finance and Economics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-7438","authenticated-orcid":false,"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Jurong West, Singapore"}]}],"member":"263","reference":[{"key":"ref1","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume-title":"Proc. TARK","author":"Boutilier"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124365"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3352584"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3379166"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3385412"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3358894"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3367237"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3580092"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2022.02533"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5565"},{"key":"ref13","first-page":"1","article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","volume-title":"Proc. ICLR","author":"Tang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.65109\/JCLE4281"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"ref16","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid"},{"key":"ref17","first-page":"980","article-title":"Unifying temporal and structural credit assignment problems","volume-title":"Proc. 3rd Int. Joint Conf. AutonomousAgents Multiagent Syst. (AAMAS)","author":"Agogino"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082486"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","first-page":"8102","article-title":"Credit assignment for collective multiagent RL with global rewards","volume-title":"Proc. NeuIPS","volume":"31","author":"Nguyen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"ref22","volume-title":"A Course in Game Theory","volume":"1","author":"Osborne","year":"1994"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.05.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467420"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811626"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.908353"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref29","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Son"},{"key":"ref30","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/rgzc7194"},{"key":"ref32","first-page":"462","article-title":"Multiagent model-based credit assignment for continuous control","volume-title":"Proc. AAMAS","author":"Han"},{"key":"ref33","first-page":"1","article-title":"SHAQ: Incorporating Shapley value theory into multi-agent Q-learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref36","first-page":"2164","article-title":"Monte\u2013Carlo planning in large POMDPs","volume-title":"Proc. 23rd Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Silver"},{"key":"ref37","first-page":"4476","article-title":"Learning and planning in complex action spaces","volume-title":"Proc. ICML","author":"Hubert"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6208"},{"key":"ref39","first-page":"1814","article-title":"Multiagent rollout and policy iteration for POMDP with application to multi-robot repair problems","volume-title":"Proc. CoRL","author":"Bhattacharya"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.65109\/sbjb8939"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.65109\/ylrm4836"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/12"},{"key":"ref43","first-page":"1","article-title":"Multi-agent reinforcement learning with hierarchical coordination for emergency responder stationing","volume-title":"Proc. ICML","author":"Sivagnanam"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918755924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/64"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.65109\/vnpx2475"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9439"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref49","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref50","first-page":"1","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Zhou"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26364"},{"key":"ref52","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. NeuIPS\u201921","author":"Peng"},{"key":"ref53","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref54","first-page":"1","article-title":"Non-linear coordination graphs","volume-title":"Proc. NeurIPS","author":"Kang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.65109\/czoy2835"},{"key":"ref56","first-page":"1","article-title":"Context-aware sparse deep coordination graphs","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref57","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","volume":"32","author":"Du"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MRS50823.2021.9620607"},{"key":"ref59","first-page":"1","article-title":"F2A2: Flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning","volume":"23","author":"Li","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2004.09.003"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.65109\/kque1089"},{"key":"ref62","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref63","first-page":"227","article-title":"Coordinated reinforcement learning","volume-title":"Proc. ICML","author":"Guestrin"},{"issue":"65","key":"ref64","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"Kok","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7886"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8886"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.08.014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.65109\/mphg3605"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103381"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1000"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9046-9"},{"key":"ref74","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume-title":"Proc. ICML","author":"Lauer"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.65109\/bsui8234"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11289507.pdf?arnumber=11289507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:43:05Z","timestamp":1770961385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11289507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3641970","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}