{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T01:08:56Z","timestamp":1766106536092,"version":"3.48.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Defense Science and Technology Innovation Special Zone Project","award":["1916311LZ001003"],"award-info":[{"award-number":["1916311LZ001003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10489-025-06951-y","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:24:39Z","timestamp":1763551479000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-task reinforcement learning via mixture-of-patterns meta-learning"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0996-436X","authenticated-orcid":false,"given":"Zhixiong","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiruo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"issue":"6","key":"6951_CR1","doi-asserted-by":"publisher","first-page":"5209","DOI":"10.1109\/TCYB.2020.3028378","volume":"52","author":"Z Xu","year":"2022","unstructured":"Xu Z, Chen X, Cao L (2022) Fast task adaptation based on the combination of model-based and gradient-based meta learning. IEEE Trans Cybern 52(6):5209\u20135218. https:\/\/doi.org\/10.1109\/TCYB.2020.3028378","journal-title":"IEEE Trans Cybern"},{"issue":"3","key":"6951_CR2","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TCYB.2020.2984670","volume":"52","author":"H Zhu","year":"2022","unstructured":"Zhu H, Li L, Wu J, Zhao S, Ding G, Shi G (2022) Personalized image aesthetics assessment via meta-learning with bilevel gradient optimization. IEEE Trans Cybern 52(3):1798\u20131811. https:\/\/doi.org\/10.1109\/TCYB.2020.2984670","journal-title":"IEEE Trans Cybern"},{"key":"6951_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3184368","volume":"71","author":"Y Chang","year":"2022","unstructured":"Chang Y, Chen J, He S, Pan T (2022) Similarity metric-based metalearning network combining prior metatraining strategy for intelligent fault detection under small samples prerequisite. IEEE Trans Instrum Meas 71:1\u201314. https:\/\/doi.org\/10.1109\/TIM.2022.3184368","journal-title":"IEEE Trans Instrum Meas"},{"issue":"3","key":"6951_CR4","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TSUSC.2023.3251302","volume":"8","author":"L Chen","year":"2023","unstructured":"Chen L, Meng F, Zhang Y (2023) Fast human-in-the-loop control for HVAC systems via meta-learning and model-based offline reinforcement learning. IEEE Trans Sustain Comput 8(3):504\u2013521. https:\/\/doi.org\/10.1109\/TSUSC.2023.3251302","journal-title":"IEEE Trans Sustain Comput"},{"key":"6951_CR5","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.neunet.2023.07.031","volume":"166","author":"D Vlasov","year":"2023","unstructured":"Vlasov D, Minnekhanov A, Rybka R et al (2023) Memristor-based spiking neural network with online reinforcement learning. Neural Netw 166:512\u2013523. https:\/\/doi.org\/10.1016\/j.neunet.2023.07.031","journal-title":"Neural Netw"},{"key":"6951_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106898","volume":"182","author":"Y Sun","year":"2025","unstructured":"Sun Y, Zhao F, Zhao Z et al (2025) Multi-compartment neuron and population encoding powered spiking neural network for deep distributional reinforcement learning. Neural Netw 182:106898. https:\/\/doi.org\/10.1016\/j.neunet.2024.106898","journal-title":"Neural Netw"},{"issue":"4","key":"6951_CR7","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.1109\/TPAMI.2024.3510627","volume":"47","author":"S Yang","year":"2025","unstructured":"Yang S, Linares-Barranco B, Wu Y et al (2025) Self-supervised high-order information bottleneck learning of spiking neural network for robust event-based optical flow estimation. IEEE Trans Pattern Anal Mach Intell 47(4):2280\u20132297. https:\/\/doi.org\/10.1109\/TPAMI.2024.3510627","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6951_CR8","doi-asserted-by":"publisher","DOI":"10.3389\/FNCOM.2021.543872","volume":"15","author":"P Weidel","year":"2021","unstructured":"Weidel P, Duarte RC, Morrison A (2021) Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks. Front Comput Neurosci 15:543872. https:\/\/doi.org\/10.3389\/FNCOM.2021.543872","journal-title":"Front Comput Neurosci"},{"doi-asserted-by":"publisher","unstructured":"Petit M, Dellandrea E, Chen L (2020) Bayesian optimization for developmental robotics with meta-learning by parameters bounds reduction. In: 2020 joint IEEE 10th international conference on development and learning and epigenetic robotics (ICDL-EpiRob), Valparaiso, Chile, pp 1\u20138. https:\/\/doi.org\/10.1109\/ICDL-EpiRob48136.2020.9278071","key":"6951_CR9","DOI":"10.1109\/ICDL-EpiRob48136.2020.9278071"},{"doi-asserted-by":"publisher","unstructured":"Zhang S, Zhou Y, Qu H, Zhu Y, You L (2022) Reinforcement learning based incentive mechanism for federated meta learning: a game-theoretic perspective. In: 2022 IEEE 34th international conference on tools with artificial intelligence (ICTAI), Macao, China, pp 1152\u20131159. https:\/\/doi.org\/10.1109\/ICTAI56018.2022.00176","key":"6951_CR10","DOI":"10.1109\/ICTAI56018.2022.00176"},{"doi-asserted-by":"publisher","unstructured":"Tsang H, Salahuddin MA, Limam N, Boutaba R (2023) Meta-ATMoS+: a meta-reinforcement learning framework for threat mitigation in software-defined networks. In: 2023 IEEE 48th conference on local computer networks (LCN), Daytona Beach, FL, USA, pp 1\u20139. https:\/\/doi.org\/10.1109\/LCN58197.2023.10223403","key":"6951_CR11","DOI":"10.1109\/LCN58197.2023.10223403"},{"issue":"2","key":"6951_CR12","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/LCOMM.2021.3110775","volume":"26","author":"N Yang","year":"2022","unstructured":"Yang N et al (2022) Specific emitter identification with limited samples: a model-agnostic meta-learning approach. IEEE Commun Lett 26(2):345\u2013349. https:\/\/doi.org\/10.1109\/LCOMM.2021.3110775","journal-title":"IEEE Commun Lett"},{"key":"6951_CR13","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxad089","author":"Z Xu","year":"2023","unstructured":"Xu Z, Zhang W, Li A, Zhao F, Jing Y, Wan Z, Cao L, Chen X (2023) Online optimization method of learning process for meta-learning. Comput J. https:\/\/doi.org\/10.1093\/comjnl\/bxad089","journal-title":"Comput J"},{"key":"6951_CR14","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.neucom.2021.12.086","volume":"478","author":"X Liu","year":"2022","unstructured":"Liu X, Wu J, Chen S (2022) A context-based meta-reinforcement learning approach to efficient hyperparameter optimization. Neurocomputing 478:89\u2013103","journal-title":"Neurocomputing"},{"doi-asserted-by":"publisher","unstructured":"Guan Y, Liu Y, Zhou K, Huang J (2023) Hierarchical meta-learning with hyper-tasks for few-shot learning. In: Proceedings of the 32nd ACM international conference on information and knowledge management (CIKM '23). Association for computing machinery, New York, NY, USA, pp 587\u2013596. https:\/\/doi.org\/10.1145\/3583780.361491","key":"6951_CR15","DOI":"10.1145\/3583780.361491"},{"issue":"2","key":"6951_CR16","doi-asserted-by":"publisher","DOI":"10.1145\/3539576","volume":"20","author":"W Gong","year":"2023","unstructured":"Gong W, Zhang Y, Wang W, Cheng P, Gonz\u00e0lez J (2023) Meta-mmfnet: meta-learning-based multi-model fusion network for micro-expression recognition. ACM Trans Multimed Comput Commun Appl 20(2):39. https:\/\/doi.org\/10.1145\/3539576","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"issue":"4","key":"6951_CR17","doi-asserted-by":"publisher","DOI":"10.1145\/3591362","volume":"14","author":"Y Gao","year":"2023","unstructured":"Gao Y, Wang P, Liu L, Zhang C, Ma H (2023) Configure your federation: hierarchical attention-enhanced meta-learning network for personalized federated learning. ACM Trans Intell Syst Technol 14(4):24. https:\/\/doi.org\/10.1145\/3591362","journal-title":"ACM Trans Intell Syst Technol"},{"unstructured":"Kim J et al (2024) Skills regularized task decomposition for multi-task offline reinforcement learning. Proc Int Conf Learn Represent 1\u201322","key":"6951_CR18"},{"unstructured":"Li W, Qiao D, Wang B, Wang X, Jin B, Zha H (2023) SAMA: semantically aligned task decomposition in multi-agent reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/2305.10865","key":"6951_CR19"},{"key":"6951_CR20","first-page":"1","volume":"202","author":"Y Wang","year":"2024","unstructured":"Wang Y et al (2024) Modular meta-learning with shrinkage for Bayesian few-shot adaptation. Proc Int Conf Mach Learn 202:1\u201318","journal-title":"Proc Int Conf Mach Learn"},{"unstructured":"Zhang T et al (2025) RLDG: reinforcement learning-driven distillation for generalist robot policies. Robot: Sci Syst 1\u201315","key":"6951_CR21"},{"issue":"5","key":"6951_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2025.3557590","volume":"36","author":"L Chen","year":"2025","unstructured":"Chen L et al (2025) MG2L: global-to-local task representation for multi-agent meta-reinforcement learning. IEEE Trans Neural Netw Learn Syst 36(5):1\u201315","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6951_CR23","first-page":"1","volume":"168","author":"X Liu","year":"2025","unstructured":"Liu X et al (2025) CausalCOMRL: context-based offline meta-reinforcement learning with causal representation. Neural Netw 168:1\u201315","journal-title":"Neural Netw"},{"key":"6951_CR24","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1613\/jair.731","volume":"12","author":"J Baxter","year":"2000","unstructured":"Baxter J et al (2000) A model of inductive bias learning. J Artif Intell Res (JAIR) 12:149\u2013198 (3)","journal-title":"J Artif Intell Res (JAIR)"},{"doi-asserted-by":"crossref","unstructured":"Caruana R (1998) Multitask learning. In: Learning to learn. Springer, pp 95\u2013133","key":"6951_CR25","DOI":"10.1007\/978-1-4615-5529-2_5"},{"unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks. Preprint at https:\/\/arxiv.org\/abs\/1706.05098","key":"6951_CR26"},{"doi-asserted-by":"crossref","unstructured":"Caruna R (1993) Multitask learning: a knowledge-based source of inductive bias. In: Machine learning: proceedings of the tenth international conference, pp 41\u201348","key":"6951_CR27","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"doi-asserted-by":"publisher","unstructured":"Li D, Zhang Z, Yuan S, Gao M, Zhang W, Yang C, Liu X, Yang J (2023) AdaTT: adaptive task-to-task fusion network for multitask learning in recommendations. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (KDD '23). Association for computing machinery, New York, NY, USA, pp 4370\u20134379. https:\/\/doi.org\/10.1145\/3580305.3599769","key":"6951_CR28","DOI":"10.1145\/3580305.3599769"},{"issue":"2","key":"6951_CR29","doi-asserted-by":"publisher","DOI":"10.1145\/3617827","volume":"42","author":"H Liu","year":"2023","unstructured":"Liu H, Wei Y, Liu F, Wang W, Nie L, Chua T-S (2023) Dynamic multimodal fusion via meta-learning towards micro-video recommendation. ACM Trans Inf Syst 42(2):26. https:\/\/doi.org\/10.1145\/3617827","journal-title":"ACM Trans Inf Syst"},{"issue":"7","key":"6951_CR30","doi-asserted-by":"publisher","first-page":"3614","DOI":"10.1109\/TPAMI.2021.3054719","volume":"44","author":"S Vandenhende","year":"2022","unstructured":"Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L (2022) Multi-task learning for dense prediction tasks: a survey. IEEE Trans Pattern Anal Mach Intell 44(7):3614\u20133633. https:\/\/doi.org\/10.1109\/TPAMI.2021.3054719","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"6951_CR31","doi-asserted-by":"publisher","first-page":"5517","DOI":"10.1109\/TII.2022.3193414","volume":"19","author":"W Chen","year":"2023","unstructured":"Chen W, Zhai C, Wang X, Li J, Lv P, Liu C (2023) GCN- and GRU-based intelligent model for temperature prediction of local heating surfaces. IEEE Trans Ind Inform 19(4):5517\u20135529. https:\/\/doi.org\/10.1109\/TII.2022.3193414","journal-title":"IEEE Trans Ind Inform"},{"issue":"10","key":"6951_CR32","doi-asserted-by":"publisher","first-page":"7120","DOI":"10.1109\/TCSVT.2022.3169842","volume":"32","author":"Y Hao","year":"2022","unstructured":"Hao Y et al (2022) Attention in attention: modeling context correlation for efficient video classification. IEEE Trans Circuits Syst Video Technol 32(10):7120\u20137132. https:\/\/doi.org\/10.1109\/TCSVT.2022.3169842","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) Openai gym. Preprint at https:\/\/arxiv.org\/abs\/1606.01540","key":"6951_CR33"},{"doi-asserted-by":"crossref","unstructured":"Todorov E, Erez T, Tassa Y (2012) Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 5026\u20135033. IEEE","key":"6951_CR34","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"3\u20134","key":"6951_CR35","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3\u20134):229\u2013256","journal-title":"Mach Learn"},{"unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: ICML, pp 741\u2013753","key":"6951_CR36"},{"doi-asserted-by":"crossref","unstructured":"Ketkar N (2017) Introduction to pytorch. Deep learning with python. Apress, Berkeley, CA, pp 195\u2013208","key":"6951_CR37","DOI":"10.1007\/978-1-4842-2766-4_12"},{"key":"6951_CR38","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple datasets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"unstructured":"Yu T, Quillen D, He Z, Julian R, Hausman K, Finn C, Levine S (2019) Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning, conference on robot learning (CoRL), pp 1094\u20131100","key":"6951_CR39"},{"issue":"5","key":"6951_CR40","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1109\/72.159058","volume":"3","author":"SK Pal","year":"1992","unstructured":"Pal SK, Mitra S (1992) Multilayer perceptron, fuzzy sets, and classification. IEEE Trans Neural Netw 3(5):683\u2013697","journal-title":"IEEE Trans Neural Netw"},{"issue":"3\u20134","key":"6951_CR41","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/S0925-2312(97)00161-6","volume":"15","author":"AC Tsoi","year":"1997","unstructured":"Tsoi AC, Back A (1997) Discrete time recurrent neural network architectures: a unifying review. Neurocomputing 15(3\u20134):183\u2013223","journal-title":"Neurocomputing"},{"issue":"8","key":"6951_CR42","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"issue":"4","key":"6951_CR43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106044","volume":"34","author":"M Liu","year":"2023","unstructured":"Liu M, Chen L, Du X et al (2023) Activated gradients for deep neural networks. IEEE Trans Neural Netw Learn Syst 34(4):13","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06951-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06951-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06951-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T01:04:30Z","timestamp":1766106270000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06951-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":43,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["6951"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06951-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"5 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Yes.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"There is no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1104"}}