{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T13:43:13Z","timestamp":1780321393369,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"STI 2030-Major Projects","award":["2022ZD0208804"],"award-info":[{"award-number":["2022ZD0208804"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473017"],"award-info":[{"award-number":["62473017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/lra.2025.3577527","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T13:43:39Z","timestamp":1749217419000},"page":"7476-7483","source":"Crossref","is-referenced-by-count":6,"title":["LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2643-5304","authenticated-orcid":false,"given":"Guobin","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, WINDY Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3098-8059","authenticated-orcid":false,"given":"Shiyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, WINDY Lab, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ado5888"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-095844"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.12.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2018.2888681"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39251-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.08.009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3444690"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013920"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3944-8"},{"key":"ref13","first-page":"40531","article-title":"Automatic intrinsic reward shaping for exploration in deep reinforcement learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Yuan","year":"2023"},{"key":"ref14","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref15","first-page":"1","article-title":"RIDE: Rewarding impact-driven exploration for procedurally-generated environments","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raileanu","year":"2020"},{"key":"ref16","first-page":"33925","article-title":"Reward shaping for reinforcement learning with an assistant reward agent","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Ma","year":"2024"},{"key":"ref17","first-page":"4649","article-title":"On learning intrinsic rewards for policy gradient methods","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zheng","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref19","first-page":"1","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu","year":"2018"},{"key":"ref20","first-page":"691","article-title":"Inverse reinforcement learning in partially observable environments","volume":"12","author":"Choi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/890"},{"key":"ref22","first-page":"67929","article-title":"Long-horizon planning for multi-agent robots in partially observable environments","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Nayak","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-024-00550-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"ref26","first-page":"58077","article-title":"To believe or not to believe your LLM: Iterativeprompting for estimating epistemic uncertainty","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Abbasi-Yadkori","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref29","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400189"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"ref32","first-page":"1","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref33","first-page":"1","article-title":"Text2Reward: Reward shaping with language models for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2024"},{"key":"ref34","article-title":"Challenges faced by large language models in solving multi-agent flocking","author":"Li","year":"2024"},{"key":"ref35","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref36","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11008675\/11027664.pdf?arnumber=11027664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T18:47:49Z","timestamp":1763578069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11027664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":36,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3577527","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}