{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:19Z","timestamp":1775529859318,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107200"],"award-info":[{"award-number":["2020AAA0107200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921006"],"award-info":[{"award-number":["61921006"]}],"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":["62022039"],"award-info":[{"award-number":["62022039"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3394513","type":"journal-article","created":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T13:33:27Z","timestamp":1718804007000},"page":"6326-6340","source":"Crossref","is-referenced-by-count":4,"title":["Multiagent Continual Coordination via Progressive Task Contextualization"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7803-0766","authenticated-orcid":false,"given":"Lei","family":"Yuan","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7017-6488","authenticated-orcid":false,"given":"Lihe","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0570-4969","authenticated-orcid":false,"given":"Ziqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5198-9141","authenticated-orcid":false,"given":"Cong","family":"Guan","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-5447","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref3","first-page":"3271","article-title":"Multi-agent reinforcement learning for active voltage control on power distribution networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref4","first-page":"20147","article-title":"Multi-agent dynamic algorithm configuration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xue"},{"key":"ref5","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"Papoudakis","year":"2019","journal-title":"arXiv:1906.04737"},{"key":"ref6","first-page":"29142","article-title":"Towards understanding cooperative multi-agent Q-learning with value factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref7","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Christianos"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref9","first-page":"4399","article-title":"\u2018Other-play\u2019 for zero-shot coordination","volume-title":"Proc. ICML","author":"Hu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00022"},{"key":"ref11","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref12","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. NeurIPS","author":"Yu"},{"key":"ref13","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 Multi Agent Syst.","author":"Sunehag"},{"key":"ref14","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref15","first-page":"5510","article-title":"Towards a standardised performance evaluation protocol for cooperative MARL","volume-title":"Proc. NeurIPS","author":"Gorsane"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref17","article-title":"A survey of ad hoc teamwork: Definitions, methods, and open problems","author":"Mirsky","year":"2022","journal-title":"arXiv:2202.10450"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref19","first-page":"3242","article-title":"Policy consolidation for continual reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Kaplanis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17006"},{"key":"ref21","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lopez-Paz"},{"key":"ref22","first-page":"1240","article-title":"Online learned continual compression with adaptive quantization modules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Caccia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20674"},{"key":"ref24","article-title":"Building a subspace of policies for scalable continual learning","volume-title":"Proc. ICLR","author":"Gaya"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref26","first-page":"8016","article-title":"Continuous coordination as a realistic scenario for lifelong learning","volume-title":"Proc. ICML","author":"Nekoei"},{"key":"ref27","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. NeurIPS","author":"Papoudakis"},{"key":"ref28","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089493"},{"key":"ref32","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref34","article-title":"Discovering generalizable multi-agent coordination skills from multi-task offline data","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref35","article-title":"Model-based multi-agent reinforcement learning: Recent progress and prospects","author":"Wang","year":"2022","journal-title":"arXiv:2203.10603"},{"key":"ref36","first-page":"844","article-title":"Contrasting centralized and decentralized critics in multi-agent reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Lyu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089834"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177461"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3228578"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-023-3862-1","article-title":"Multi-agent policy transfer via task relationship modeling","volume-title":"Proc. Deep Reinforcement Learn. Workshop","author":"Qin"},{"key":"ref44","article-title":"Heterogeneous multi-agent zero-shot coordination by coevolution","author":"Xue","year":"2022","journal-title":"arXiv:2208.04957"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00452-0"},{"issue":"13","key":"ref46","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"James","year":"2017","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"ref47","first-page":"348","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref48","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019","journal-title":"arXiv:1902.10486"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560793"},{"key":"ref50","first-page":"184","article-title":"The effectiveness of world models for continual reinforcement learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Kessler"},{"key":"ref51","article-title":"A neural Dirichlet process mixture model for task-free continual learning","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref52","article-title":"Dynamics-adaptive continual reinforcement learning via progressive contextualization","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3159661"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2023.3245729"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01316-9"},{"key":"ref57","first-page":"28496","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Wo\u0142czyk"},{"key":"ref58","first-page":"705","article-title":"CORA: Benchmarks, baselines, and metrics as a platform for continual reinforcement learning agents","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Powers"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3853-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3696-5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198503682.001.0001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref67","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref68","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"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10949581\/10562331.pdf?arnumber=10562331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:03Z","timestamp":1764959943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10562331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":70,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3394513","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}