{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:47:34Z","timestamp":1780548454613,"version":"3.54.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62376280"],"award-info":[{"award-number":["62376280"]}],"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":[[2025,6]]},"DOI":"10.1109\/lra.2025.3566585","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T17:17:59Z","timestamp":1746206279000},"page":"6280-6287","source":"Crossref","is-referenced-by-count":3,"title":["Meta-Reinforcement Learning With Evolving Gradient Regularization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-0535","authenticated-orcid":false,"given":"Jiaxing","family":"Chen","sequence":"first","affiliation":[{"name":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0849-0256","authenticated-orcid":false,"given":"Ao","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6823-555X","authenticated-orcid":false,"given":"Shaofei","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weilin","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Information and Communication, National University of Defense Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2807-8208","authenticated-orcid":false,"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104654"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref7","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2024"},{"key":"ref8","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref9","first-page":"4061","article-title":"Taming MAML: Efficient unbiased meta-reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Liu","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2037-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12183865"},{"key":"ref12","article-title":"Rapid learning or feature reuse? towards understanding the effectiveness of MAML","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Raghu","year":"2020"},{"key":"ref13","first-page":"1082","article-title":"On the convergence theory of gradient-based model-agnostic meta-learning algorithms","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Fallah","year":"2020"},{"key":"ref14","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. 3rd Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref15","first-page":"26982","article-title":"Penalizing gradient norm for efficiently improving generalization in deep learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Zhao","year":"2022"},{"key":"ref16","first-page":"22234","article-title":"EvoGrad: Efficient gradient-based meta-learning and hyperparameter optimization","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Bohdal","year":"2021"},{"issue":"5","key":"ref17","first-page":"653","article-title":"Review on meta reinforcement learning","volume":"53","author":"Tan","year":"2021","journal-title":"J. Nanjing Univ. Aeronaut. Astronaut."},{"key":"ref18","first-page":"15340","article-title":"Transformers are meta-reinforcement learners","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Melo","year":"2022,"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"Mach. Learn."},{"key":"ref20","first-page":"10","article-title":"Sharp-MAML: Sharpness-aware model-agnostic meta-learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Abbas","year":"2022"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32th Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","article-title":"Some considerations on learning to explore via meta-reinforcement learning","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Stadie","year":"2018"},{"key":"ref24","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Rothfuss","year":"2019"},{"key":"ref25","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref26","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref27","first-page":"3751","article-title":"Learned optimizers that scale and generalize","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Wichrowska","year":"2017"},{"key":"ref28","article-title":"Learning to optimize","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Li","year":"2017"},{"key":"ref29","first-page":"7959","article-title":"Fast and flexible multi-task classification using conditional neural adaptive processes","volume-title":"Proc. 33th Int. Conf. Neural Inf. Process. Syst.","author":"Requeima","year":"2019"},{"key":"ref30","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Triantafillou","year":"2020"},{"key":"ref31","article-title":"How to train your MAML","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Antoniou","year":"2019"},{"key":"ref32","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref33","article-title":"How to train your MAML to excel in few-shot classification","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Ye","year":"2022"},{"key":"ref34","first-page":"4238","article-title":"MAML and ANIL provably learn representations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Collins","year":"2022"},{"key":"ref35","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Rajeswaran","year":"2019"},{"key":"ref36","article-title":"ES-MAML: Simple hessian-free meta learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10969146\/10982140.pdf?arnumber=10982140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T06:16:03Z","timestamp":1747116963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3566585","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}