{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:49:44Z","timestamp":1782161384201,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136008"],"award-info":[{"award-number":["62136008"]}],"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":["62293541"],"award-info":[{"award-number":["62293541"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4232056"],"award-info":[{"award-number":["4232056"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484514"],"award-info":[{"award-number":["20240484514"]}],"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":[[2026,2]]},"DOI":"10.1109\/tcds.2025.3578001","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:54:47Z","timestamp":1749563687000},"page":"154-166","source":"Crossref","is-referenced-by-count":0,"title":["CPIG: Leveraging Consistency Policy With Intention Guidance for Multiagent Exploration"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9031-9889","authenticated-orcid":false,"given":"Yuqian","family":"Fu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-9585","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7756-7046","authenticated-orcid":false,"given":"Zijie","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7611-064X","authenticated-orcid":false,"given":"Jiajun","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3202185"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2840971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref5","first-page":"430","article-title":"Leveraging exploration in off-policy algorithms via normalizing flows","volume-title":"Proc. Conf. Robot Learn.","author":"Mazoure","year":"2020"},{"key":"ref6","first-page":"13957","article-title":"Reparameterized policy learning for multimodal trajectory optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref7","article-title":"NoMaD: Goal masked diffusion policies for navigation and exploration","volume-title":"Proc. NeurIPS Found. Models Decis. Making Workshop","author":"Sridhar","year":"2023"},{"key":"ref8","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref9","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kuba","year":"2022"},{"key":"ref10","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3368055"},{"key":"ref12","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref13","article-title":"Probabilistic mixture-of-experts for efficient deep reinforcement learning","author":"Ren","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref15","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song","year":"2021"},{"key":"ref16","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","year":"2023"},{"key":"ref17","first-page":"67195","article-title":"Efficient diffusion policies for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3387401"},{"key":"ref19","article-title":"Influence-based multi-agent exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","year":"2020"},{"key":"ref20","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3557694"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26385"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3233\/faia230493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3268076"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111663"},{"key":"ref27","first-page":"12008","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Peng","year":"2021"},{"key":"ref28","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref29","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zheng","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146201"},{"key":"ref31","article-title":"Diffusion models for reinforcement learning: A survey","author":"Zhu","year":"2023"},{"key":"ref32","article-title":"Is conditional generative modeling all you need for decision making?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ajay","year":"2023"},{"key":"ref33","article-title":"Reasoning with latent diffusion in offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Venkatraman","year":"2024"},{"key":"ref34","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Janner","year":"2022"},{"key":"ref35","first-page":"4177","article-title":"MADiff: Offline multi-agent learning with diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu","year":"2024"},{"key":"ref36","article-title":"Beyond conservatism: Diffusion policies in offline multi-agent reinforcement learning","author":"Li","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309608"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.65109\/awzc1597"},{"key":"ref39","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.65109\/ckwc1742"},{"key":"ref41","article-title":"Consistency models as a rich and efficient policy class for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ding","year":"2024"},{"key":"ref42","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref44","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref45","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3487535"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802212"},{"key":"ref48","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref49","first-page":"39842","article-title":"Generative modelling of stochastic actions with arbitrary constraints in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2023"},{"key":"ref50","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh","year":"2018"},{"key":"ref51","first-page":"13964","article-title":"Self-imitation learning via generalized lower bound Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2020"},{"issue":"32","key":"ref52","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen","year":"2022"},{"key":"ref54","first-page":"4333","article-title":"Memory based trajectory-conditioned policies for learning from sparse rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.65109\/gash9357"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","first-page":"2753","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tang","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3510428"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3370219"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11392775\/11029514.pdf?arnumber=11029514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:58:31Z","timestamp":1782158311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":60,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3578001","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}