{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:34:09Z","timestamp":1780515249769,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473320"],"award-info":[{"award-number":["62473320"]}],"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":[[2025,9]]},"DOI":"10.1109\/lra.2025.3588784","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:43:54Z","timestamp":1752601434000},"page":"8650-8657","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs"],"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":"WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9216-8403","authenticated-orcid":false,"given":"Hongyin","family":"Zhang","sequence":"additional","affiliation":[{"name":"MiLAB Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1359-6440","authenticated-orcid":false,"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"MiLAB Lab, Department of Artificial Intelligence, 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":"WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184795"},{"key":"ref6","first-page":"1","article-title":"Discovering generalizable multi-agent coordination skills from multi-task offline data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref8","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Omidshafiei","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref10","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref13","first-page":"1","article-title":"Actor-Mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Parisotto","year":"2016"},{"key":"ref14","article-title":"Policy distillation","author":"Rusu","year":"2015"},{"key":"ref15","first-page":"15146","article-title":"Knowledge transfer in multi-task deep reinforcement learning for continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2020"},{"key":"ref16","first-page":"21495","article-title":"PaCo: Parameter-compositional multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060403"},{"key":"ref20","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Andreas","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366414"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref24","article-title":"RSG: Fast learning adaptive skills for quadruped robots by skill graph","author":"Zhang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070843"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8870"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116964"},{"key":"ref30","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bordes","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/acf33a"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3072740"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat3536"},{"key":"ref34","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA62789.2024.10591921"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11082640\/11078920.pdf?arnumber=11078920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T04:50:24Z","timestamp":1752900624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":35,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3588784","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}