{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:05:49Z","timestamp":1768338349473,"version":"3.49.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312186","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"4167-4173","source":"Crossref","is-referenced-by-count":3,"title":["Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Donglin","family":"Zhan","sequence":"first","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo F.","family":"Toso","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Anderson","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"902","article-title":"Meta-learning linear quadratic regulators: a policy gradient maml approach for model-free lqr","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Toso"},{"key":"ref2","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref3","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref4","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341571"},{"key":"ref6","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"International Conference on Machine Learning","author":"Mirzasoleiman"},{"key":"ref7","article-title":"Towards sustainable learning: Coresets for data-efficient deep learning","author":"Yang","year":"2023"},{"key":"ref8","article-title":"Diverse client selection for federated learning via submodular max-imization","volume-title":"International Conference on Learning Representations","author":"Balakrishnan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00782"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00805"},{"key":"ref11","article-title":"Promp: Proximal meta-policy search","author":"Rothfuss","year":"2018"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312186","article-title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","author":"Zhan","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref14","first-page":"20 532","article-title":"Information-theoretic task selection for meta-reinforcement learning","volume":"33","author":"Luna Gutierrez","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"ES-MAML: Simple Hessian-free meta learning","author":"Song","year":"2019"},{"key":"ref16","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International conference on machine learning","author":"Fazel"},{"key":"ref17","article-title":"Multi-task imitation learning for linear dynamical systems","volume-title":"Learning for Dynamics and Control Conference","author":"Zhang"},{"key":"ref18","article-title":"Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach","author":"Wang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110741"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC56724.2024.10885806"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33987"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA48906.2021.9659038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383370"},{"key":"ref24","first-page":"4061","article-title":"Taming maml: Efficient unbiased meta-reinforcement learning","volume-title":"International conference on machine learning","author":"Liu"},{"key":"ref25","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"The 22nd international conference on artificial intelligence and statistics","author":"Malik"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-5060(08)70732-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref29","first-page":"4951","article-title":"Overparameterized nonlinear learning: Gradient descent takes the shortest path?","volume-title":"International Conference on Machine Learning","author":"Oymak"},{"key":"ref30","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018"},{"key":"ref31","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9099-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3037046"},{"key":"ref34","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383950"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312186.pdf?arnumber=11312186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:35:50Z","timestamp":1768293350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312186","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}