{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T19:00:43Z","timestamp":1764788443496,"version":"3.46.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","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":[{"DOI":"10.13039\/501100001809","name":"Joint Funds of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20327"],"award-info":[{"award-number":["U24A20327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2019B010155001"],"award-info":[{"award-number":["2019B010155001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010226","name":"Key Scientific Research Project of the Department of Education of Guangdong Province","doi-asserted-by":"publisher","award":["2024ZDZX3012"],"award-info":[{"award-number":["2024ZDZX3012"]}],"id":[{"id":"10.13039\/501100010226","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":[[2025,12]]},"DOI":"10.1109\/tnnls.2025.3598301","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:47:19Z","timestamp":1757526439000},"page":"20105-20119","source":"Crossref","is-referenced-by-count":0,"title":["When to Align: Dynamic Behavior Consistency for Multiagent Systems via Intrinsic Rewards"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2009-7693","authenticated-orcid":false,"given":"Kunyang","family":"Lin","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Yufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6847-1621","authenticated-orcid":false,"given":"Peihao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-3342","authenticated-orcid":false,"given":"Yinjie","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu, China"}]},{"given":"Siyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8411-6734","authenticated-orcid":false,"given":"Qing","family":"Du","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-5886","authenticated-orcid":false,"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"UMass Amherst, Amherst, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172168"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3220798"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref4","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. NeurIPS","author":"Peng"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177461"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref7","first-page":"5175","article-title":"On the utility of learning about humans for human-AI coordination","volume-title":"Proc. NeurIPS","author":"Carroll"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00045-z"},{"key":"ref11","first-page":"8304","article-title":"ELIGN: Expectation alignment as a multi-agent intrinsic reward","volume-title":"Proc. NeurIPS","author":"Ma"},{"key":"ref12","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref13","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","volume":"32","author":"Du"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref15","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"Stadie","year":"2015","journal-title":"arXiv:1507.00814"},{"key":"ref16","article-title":"Coordinated exploration via intrinsic rewards for multi-agent reinforcement learning","author":"Iqbal","year":"2019","journal-title":"arXiv:1905.12127"},{"key":"ref17","first-page":"21937","article-title":"Lazy agents: A new perspective on solving sparse reward problem in multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29711"},{"key":"ref19","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3382480"},{"key":"ref21","first-page":"1","article-title":"Generating diverse cooperative agents by learning incompatible policies","volume-title":"Proc. ICLR","author":"Charakorn"},{"key":"ref22","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref24","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2007.908472"},{"key":"ref29","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref30","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. NeurIPS","author":"Yu"},{"key":"ref31","first-page":"67","article-title":"TiZero: Mastering multi-agent football with curriculum learning and self-play","volume-title":"Proc. AAMAS","author":"Lin"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3337534"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51924-7_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3090796"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056418"},{"key":"ref37","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref38","first-page":"1801","article-title":"A new framework for multi-agent reinforcement learning-centralized training and exploration with decentralized execution via policy distillation","volume-title":"Proc. AAMAS","author":"Chen"},{"key":"ref39","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":"ref40","first-page":"590","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. CoRL","author":"Liu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102140"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3283537"},{"key":"ref43","first-page":"23049","article-title":"RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents","volume-title":"Proc. NeurIPS","author":"Qiu"},{"key":"ref44","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. JMLR","author":"Rashid"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref46","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref47","first-page":"5887","article-title":"Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Wjkde"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3563773"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3575196"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3326744"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3328732"},{"key":"ref52","first-page":"28670","article-title":"Learning active camera for multi-object navigation","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3557694"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211044946"},{"key":"ref55","first-page":"579","article-title":"AIIR-MIX: Multi-agent reinforcement learning meets attention individual intrinsic reward mixing network","volume-title":"Proc. ACML","author":"Li"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref57","first-page":"3988","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. NeurIPS","author":"Andrychowicz"},{"key":"ref58","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref59","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref61","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. NIPS","author":"Sutton"},{"key":"ref62","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman"},{"key":"ref63","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref64","first-page":"4649","article-title":"On learning intrinsic rewards for policy gradient methods","volume-title":"Proc. NeurIPS","author":"Zheng"},{"issue":"1","key":"ref65","first-page":"12275","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2021","journal-title":"JMLR"},{"key":"ref66","first-page":"3059","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. ICML","author":"Liang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176343842"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198862536.003.0008"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11272992\/11156142.pdf?arnumber=11156142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:33Z","timestamp":1764787413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11156142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3598301","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}