{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:27:55Z","timestamp":1784737675252,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62236002"],"award-info":[{"award-number":["62236002"]}],"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"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232056"],"award-info":[{"award-number":["4232056"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"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. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3501580","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T14:26:41Z","timestamp":1732199201000},"page":"9164-9177","source":"Crossref","is-referenced-by-count":14,"title":["Multi-Task Multi-Agent Reinforcement Learning With Task-Entity Transformers and Value Decomposition Training"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","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\/0009-0009-7764-0050","authenticated-orcid":false,"given":"Shangjing","family":"Huang","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"}]},{"given":"Binbin","family":"Zuo","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3270444"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00577-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309608"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102096"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref10","first-page":"1","article-title":"Updet: Universal multi-agent RL via policy decoupling with transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref11","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref12","first-page":"1615","article-title":"Prioritized tasks mining for multi-task cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Yu"},{"key":"ref13","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref14","first-page":"1","article-title":"Rt-1: Robotics transformer for real-world control at scale","volume-title":"Proc. Robot., Sci. Syst.","author":"Brohan"},{"key":"ref15","first-page":"1","article-title":"Open-world object manipulation using pre-trained vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Stone"},{"issue":"1","key":"ref16","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"issue":"1","key":"ref18","first-page":"1","article-title":"Emergence of grounded compositional language in multi-agent populations","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"32","author":"Mordatch"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"2","key":"ref23","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1007\/s11633-022-1383-7","article-title":"Offline pre-trained multi-agent decision transformer","volume":"20","author":"Meng","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"ref24","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wen"},{"key":"ref25","first-page":"1679","article-title":"TransfQMix: Transformers for leveraging the graph structure of multi-agent reinforcement learning problems","volume-title":"Proc. 2023 Int. Conf. Auto. Agents Multiagent Syst.","author":"Gallici"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref28","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"},{"key":"ref29","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sodhani"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25825"},{"issue":"11","key":"ref31","first-page":"12376","article-title":"Not all tasks are equally difficult: Multi-task deep reinforcement learning with dynamic depth routing","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"He"},{"key":"ref32","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Omidshafiei"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/pr11010267"},{"issue":"3","key":"ref34","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1109\/TG.2023.3316697","article-title":"Deep multi-task multi-agent reinforcement learning with knowledge transfer","volume":"16","author":"Mai","year":"2023","journal-title":"IEEE Trans. Games"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP60502.2023.10387119"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2024.3403715"},{"key":"ref37","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","article-title":"Multi-agent reinforcement learning as a rehearsal for decentralized planning","volume":"190","author":"Kraemer","year":"2016","journal-title":"Neurocomputing"},{"key":"ref39","first-page":"9927","article-title":"Multi-agent common knowledge reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Schroeder de Witt"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"ref42","first-page":"4157","article-title":"Environment generation for zero-shot compositional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gur"},{"key":"ref43","first-page":"1","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process","author":"Reimers"},{"issue":"140","key":"ref44","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3236805"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109631","article-title":"Knowledge-enhanced reinforcement learning for multi-machine integrated production and maintenance scheduling","volume":"185","author":"Hu","year":"2023","journal-title":"Comput. Ind. Eng."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TEMPR.2024.3372656"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"ref49","first-page":"281","article-title":"Aligning credit for multi-agent cooperation via model-based counterfactual imagination","volume-title":"Proc. 23rd Int. Conf. Auto. Agents Multiagent Syst.","author":"Chai"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10759737.pdf?arnumber=10759737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:42:33Z","timestamp":1773862953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10759737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3501580","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}