{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:39:45Z","timestamp":1782315585953,"version":"3.54.5"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133478","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:27:07Z","timestamp":1774970827000},"page":"133478","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Curiosity-driven decision causal-convolutional transformer with adaptive training for offline-to-online multi-agent reinforcement learning"],"prefix":"10.1016","volume":"684","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5781-4068","authenticated-orcid":false,"given":"Bohang","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6656-6061","authenticated-orcid":false,"given":"Weiqiang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3651-0702","authenticated-orcid":false,"given":"Biao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.neucom.2026.133478_bib0005","first-page":"73","article-title":"A survey on multi-agent reinforcement learning and its application","volume":"3","author":"Ning","year":"2024","journal-title":"J. Autom. Intell."},{"issue":"2","key":"10.1016\/j.neucom.2026.133478_bib0010","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","article-title":"Multi-agent deep reinforcement learning: a survey","volume":"55","author":"Gronauer","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.neucom.2026.133478_bib0015","author":"Jin"},{"issue":"1","key":"10.1016\/j.neucom.2026.133478_bib0020","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TRO.2022.3200138","article-title":"Partially observable markov decision processes in robotics: a survey","volume":"39","author":"Lauri","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133478_bib0025","series-title":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","first-page":"1","article-title":"Deploying reinforcement learning approaches for smart home Automation","author":"Sen","year":"2024"},{"key":"10.1016\/j.neucom.2026.133478_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2024.114648","article-title":"An overview of reinforcement learning-based approaches for smart home energy management systems with energy storages","volume":"202","author":"Pinthurat","year":"2024","journal-title":"Renew. Sustain. Energy Rev."},{"issue":"7","key":"10.1016\/j.neucom.2026.133478_bib0035","doi-asserted-by":"crossref","DOI":"10.3390\/s23073625","article-title":"Multi-agent deep reinforcement learning for multi-robot applications: a survey","volume":"23","author":"Orr","year":"2023","journal-title":"Sensors"},{"issue":"3","key":"10.1016\/j.neucom.2026.133478_bib0040","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1109\/TCDS.2024.3504256","article-title":"Smart: sequential multiagent reinforcement learning with role assignment using transformer","volume":"17","author":"Lan","year":"2025","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"1","key":"10.1016\/j.neucom.2026.133478_bib0045","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.ejor.2020.09.018","article-title":"Multi-agent reinforcement learning algorithm to solve a partially-observable multi-agent problem in disaster response","volume":"291","author":"Lee","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.neucom.2026.133478_bib0050","series-title":"City, Society, and Digital Transformation","first-page":"345","article-title":"Complex task assignment of aviation emergency rescue based on multiagent reinforcement learning","author":"Shen","year":"2022"},{"issue":"10","key":"10.1016\/j.neucom.2026.133478_bib0055","doi-asserted-by":"crossref","DOI":"10.3390\/s23104710","article-title":"A comprehensive survey on multi-agent reinforcement learning for connected and automated vehicles","volume":"23","author":"Yadav","year":"2023","journal-title":"Sensors"},{"issue":"8","key":"10.1016\/j.neucom.2026.133478_bib0060","doi-asserted-by":"crossref","first-page":"10237","DOI":"10.1109\/TNNLS.2023.3250269","article-title":"A survey on offline reinforcement learning: taxonomy, review, and open problems","volume":"35","author":"Figueiredo Prudencio","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133478_bib0065","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133478_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128432","article-title":"H2-marl: multi-agent reinforcement learning for pareto optimality in hospital capacity strain and human mobility during epidemic","volume":"291","author":"Luo","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133478_bib0075","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133478_bib0080","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"10.1016\/j.neucom.2026.133478_bib0085","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2022"},{"key":"10.1016\/j.neucom.2026.133478_bib0090","series-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","article-title":"Believe what you see: implicit constraint approach for offline multi-agent reinforcement learning","author":"Yang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133478_bib0095","series-title":"Advances in Neural Information Processing Systems","first-page":"77290","article-title":"Counterfactual conservative q learning for offline multi-agent reinforcement learning","volume":"vol. 36","author":"Shao","year":"2023"},{"key":"10.1016\/j.neucom.2026.133478_bib0100","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume":"vol. 97","author":"Fujimoto","year":"2019"},{"key":"10.1016\/j.neucom.2026.133478_bib0105","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"An optimistic perspective on offline reinforcement learning","author":"Agarwal","year":"2020"},{"key":"10.1016\/j.neucom.2026.133478_bib0110","series-title":"Advances in Neural Information Processing Systems","first-page":"15084","article-title":"Decision transformer: reinforcement learning via sequence modeling","volume":"vol. 34","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.133478_bib0115","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Decision convformer: local filtering in metaformer is sufficient for decision making","author":"Kim","year":"2024"},{"key":"10.1016\/j.neucom.2026.133478_bib0120","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Long-short decision transformer: bridging global and local dependencies for generalized decision-making","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133478_bib0125","series-title":"Advances in Neural Information Processing Systems","first-page":"4177","article-title":"Madiff: offline multi-agent learning with diffusion models","volume":"vol. 37","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133478_bib0130","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"27042","article-title":"Online decision transformer","volume":"vol. 162","author":"Zheng","year":"2022"},{"issue":"2","key":"10.1016\/j.neucom.2026.133478_bib0135","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":"10.1016\/j.neucom.2026.133478_bib0140","article-title":"Parameter-efficient fine-tuning for large models: a comprehensive survey","author":"Han","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133478_bib0145","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"issue":"11","key":"10.1016\/j.neucom.2026.133478_bib0150","doi-asserted-by":"crossref","first-page":"12862","DOI":"10.1109\/TPAMI.2022.3204708","article-title":"Starformer: transformer with state-action-reward representations for robot learning","volume":"45","author":"Shang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133478_bib0155","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Value-aligned behavior cloning for offline reinforcement learning via bi-level optimization","author":"Jiang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133478_bib0160","author":"Yu"},{"key":"10.1016\/j.neucom.2026.133478_bib0165","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"10.1016\/j.neucom.2026.133478_bib0170","series-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.65109\/JSRC7365","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"Sunehag","year":"2018"},{"key":"10.1016\/j.neucom.2026.133478_bib0175","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"key":"10.1016\/j.neucom.2026.133478_bib0180","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"4295","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"vol. 80","author":"Rashid","year":"2018"},{"key":"10.1016\/j.neucom.2026.133478_bib0185","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Weighted qmix: expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2020"},{"key":"10.1016\/j.neucom.2026.133478_bib0190","series-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.65109\/SKOP8447","article-title":"Ma-mix: value function decomposition for cooperative multiagent reinforcement learning based on multi-head attention mechanism","author":"Niu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133478_bib0195","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"5887","article-title":"QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume":"vol. 97","author":"Son","year":"2019"},{"key":"10.1016\/j.neucom.2026.133478_bib0200","author":"Yang"},{"key":"10.1016\/j.neucom.2026.133478_bib0205","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","article-title":"QPLEX: duplex dueling multi-agent q-learning","author":"Wang","year":"2021"},{"issue":"9","key":"10.1016\/j.neucom.2026.133478_bib0210","doi-asserted-by":"crossref","first-page":"12873","DOI":"10.1109\/TNNLS.2023.3265358","article-title":"Multiagent trust region policy optimization","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133478_bib0215","series-title":"Advances in Neural Information Processing Systems","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"vol. 33","author":"Zhou","year":"2020"},{"key":"10.1016\/j.neucom.2026.133478_bib0220","series-title":"International Conference on Learning Representations","article-title":"Rode: learning roles to decompose multi-agent tasks","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133478_bib0225","author":"Levine"},{"key":"10.1016\/j.neucom.2026.133478_bib0230","series-title":"Proceedings of the 40th International Conference on Machine Learning","article-title":"Q-learning decision transformer: leveraging dynamic programming for conditional sequence modelling in offline RL","author":"Yamagata","year":"2023"},{"key":"10.1016\/j.neucom.2026.133478_bib0235","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","article-title":"Offline multi-agent reinforcement learning with knowledge distillation","author":"Tseng","year":"2022"},{"key":"10.1016\/j.neucom.2026.133478_bib0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129079","article-title":"Using offline data to speed up reinforcement learning in procedurally generated environments","volume":"618","author":"Andres","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133478_bib0245","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126281","article-title":"Aid-rl: active information-directed reinforcement learning for autonomous source seeking and estimation","volume":"544","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133478_bib0250","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neucom.2022.09.109","article-title":"Reinforcement learning facilitates an optimal interaction intensity for cooperation","volume":"513","author":"Song","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133478_bib0255","series-title":"ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023 - Frontiers in Artificial Intelligence and Applications","first-page":"1148","article-title":"Offline decentralized multi-agent reinforcement learning","volume":"vol. 372","author":"Jiang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133478_bib0260","author":"Mao"},{"key":"10.1016\/j.neucom.2026.133478_bib0265","series-title":"International Conference on Learning Representations (ICLR)","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2016"},{"key":"10.1016\/j.neucom.2026.133478_bib0270","author":"Samvelyan"},{"key":"10.1016\/j.neucom.2026.133478_bib0275","series-title":"Thirty-Seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","first-page":"37567","article-title":"Smacv2: an improved benchmark for cooperative multi-agent reinforcement learning","volume":"vol. 36","author":"Ellis","year":"2023"},{"key":"10.1016\/j.neucom.2026.133478_bib0280","series-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"5026","article-title":"Mujoco: a Physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.neucom.2026.133478_bib0285","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"12208","article-title":"Facmac: factored multi-agent centralised policy gradients","volume":"vol. 34","author":"Peng","year":"2021"},{"key":"10.1016\/j.neucom.2026.133478_bib0290","series-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","article-title":"A minimalist approach to offline reinforcement learning","author":"Fujimoto","year":"2021"},{"key":"10.1016\/j.neucom.2026.133478_bib0295","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"17221","article-title":"Plan better amid conservatism: offline multi-agent reinforcement learning with actor rectification","volume":"vol. 162","author":"Pan","year":"2022"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008751?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008751?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T23:44:49Z","timestamp":1777333489000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226008751"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":59,"alternative-id":["S0925231226008751"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133478","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Curiosity-driven decision causal-convolutional transformer with adaptive training for offline-to-online multi-agent reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133478","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133478"}}