{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:05:20Z","timestamp":1755907520138,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107675","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"166-173","source":"Crossref","is-referenced-by-count":0,"title":["Learning Effective and Generalizable Controller via Zeroth-order Gradient Estimation"],"prefix":"10.23919","author":[{"given":"Chaodong","family":"Li","sequence":"first","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"}]},{"given":"Peng","family":"Yi","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"}]},{"given":"Wenting","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"}]},{"given":"Di","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongji University,Department of Control Science and Engineering,Shanghai,China,201804"}]},{"given":"Wenyan","family":"Bai","sequence":"additional","affiliation":[{"name":"Beijing Aerospace Automatic Control Institute,Beijing,China,100854"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00186-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2018.08.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abh1221"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adh5401"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107266"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3368026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160581"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374611"},{"article-title":"Deepzero: Scaling up zeroth-order optimization for deep model training","year":"2023","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"article-title":"How to robustify black-box ml models? a zeroth-order optimization perspective","year":"2022","author":"Zhang","key":"ref13"},{"key":"ref14","first-page":"6111","article-title":"Solver-in-the-loop: Learning from differentiable physics to interact with iterative pde-solvers","volume":"33","author":"Um","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Revisiting zeroth-order optimization for memory-efficient llm fine-tuning: A benchmark","year":"2024","author":"Zhang","key":"ref15"},{"article-title":"Meta-learning linear quadratic regulators: A policy gradient maml approach for the modelfree lqr","year":"2024","author":"Toso","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109947"},{"key":"ref18","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Neuromancer: Neural modules with adaptive nonlinear constraints and efficient regularizations","year":"2021","author":"Tuor","key":"ref19"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref20"},{"key":"ref21","first-page":"1147","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Conference on Robot Learning","author":"Song"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1515\/9781400840601"}],"event":{"name":"2025 American Control Conference (ACC)","start":{"date-parts":[[2025,7,8]]},"location":"Denver, CO, USA","end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107675.pdf?arnumber=11107675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:33:21Z","timestamp":1755840801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":22,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107675","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}