{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:19:08Z","timestamp":1768004348791,"version":"3.49.0"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886215","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"6108-6115","source":"Crossref","is-referenced-by-count":2,"title":["Parametric PDE Control with Deep Reinforcement Learning and L<sub>0<\/sub> Sparse Polynomial Policies"],"prefix":"10.1109","author":[{"given":"Nicol\u00f2","family":"Botteghi","sequence":"first","affiliation":[{"name":"University of Twente,Department of Applied Mathematics,The Netherlands"}]},{"given":"Urban","family":"Fasel","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Aeronautics,United Kingdom"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77226-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718607"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/112"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2018.0335"},{"key":"ref6","article-title":"Optimal control and estimation","author":"Stengel","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2017.02.027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/1.J061518"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cep.2007.11.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1768-8_11"},{"key":"ref11","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.29007\/xtgm"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref15","article-title":"Learning sparse neural networks through 1_0 regularization","volume-title":"International Conference on Learning Representations","author":"Louizos"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1517384113"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref21","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019","journal-title":"arXiv:1912.10944"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref25","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International conference on machine learning.","author":"Wang"},{"key":"ref26","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1992"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref29","article-title":"On reward shaping for mobile robot navigation: A reinforcement learning and slam based approach","author":"Botteghi","year":"2020","journal-title":"arXiv:2002.04109"},{"key":"ref30","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","volume-title":"Australasian Conference on Robotics and Automation 2015. Australian Robotics and Automation Association (ARAA)","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635936"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28957-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/14685248.2020.1797059"},{"key":"ref36","article-title":"Optimal control of point-to-point navigation in turbulent time dependent flows using reinforcement learning","author":"Buzzicotti","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s42241-020-0028-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1063\/5.0143913"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2004939117"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1063\/1.5116415"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2024.69"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2024.134096"},{"key":"ref43","article-title":"SINDy-RL: Interpretable and efficient model-based reinforcement learning","author":"Zolman","year":"2024","journal-title":"arXiv preprint arXiv:2403.09110"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref45","article-title":"Unsupervised representation learning in deep reinforcement learning: A review","author":"Botteghi","year":"2022","journal-title":"arXiv preprint arXiv:2208.14226"},{"key":"ref46","article-title":"Imitation learning: A survey of learning methods","author":"Hussein","year":"2017","journal-title":"ACM Comput. Surv."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"issue":"9","key":"ref51","first-page":"5149","article-title":"Metalearning in neural networks: A survey","volume":"44","author":"Hospedales","year":"2021","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019956318069"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref54","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref56","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"International Conference on Machine Learning.","author":"Molchanov"},{"key":"ref57","article-title":"Soft weight-sharing for neural network compression","volume-title":"International Conference on Learning Representations","author":"Ullrich"},{"key":"ref58","article-title":"Sparse identification of nonlinear dynamics with control (SINDYc)","author":"Brunton","year":"2016","journal-title":"IFAC"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0904"},{"key":"ref60","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint arXiv:1509.02971"},{"key":"ref61","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref62","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning.","author":"Haarnoja"},{"key":"ref63","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning.","author":"Fujimoto"},{"key":"ref64","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016","journal-title":"arXiv preprint arXiv:1611.00712"},{"key":"ref65","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv:1611.01144"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886528"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023625"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref69","article-title":"Hypersindy: Deep generative modeling of nonlinear stochastic governing equations","author":"Jacobs","year":"2023","journal-title":"arXiv preprint arXiv:2310.04832"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/0375-9601(90)90449-X"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886215.pdf?arnumber=10886215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:24:57Z","timestamp":1740641097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886215","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}