{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:25:25Z","timestamp":1742646325000,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/smc53992.2023.10394648","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:32:04Z","timestamp":1706553124000},"page":"3385-3391","source":"Crossref","is-referenced-by-count":2,"title":["ReACT: Reinforcement Learning for Controller Parametrization Using B-Spline Geometries"],"prefix":"10.1109","author":[{"given":"Thomas","family":"Rudolf","sequence":"first","affiliation":[{"name":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering department,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Fl\u00f6gel","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering department,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Sch\u00fcrmann","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering department,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"S\u00fc\u00df","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering department,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schwab","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering department,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00f6ren","family":"Hohmann","sequence":"additional","affiliation":[{"name":"Institute of Control Systems of the Karlsruhe Institute of Technology,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(00)00058-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s42401-021-00104-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107760"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/acs.3106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.09.173"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2022.08.002"},{"key":"ref7","article-title":"Data-driven calibration of thermal management control systems of an electric sports car","volume-title":"Proceedings of the 32th Aachen Colloquium Sustainable Mobility","author":"Muhl","year":"2022"},{"volume-title":"Reinforcement Learning. An Introduction, 2nd ed., ser. Adaptive Computation and Machine Learning","year":"2018","author":"Sutton","key":"ref8"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref10","article-title":"Dropout Q-functions for doubly efficient reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Hiraoka","year":"2022"},{"key":"ref11","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"Proceedings of the 37th International Conference on Machine Learning. PMLR","volume":"119","author":"Kuznetsov","year":"2020"},{"volume-title":"Curves and Surfaces for CAGD. A Practical Guide","year":"2002","author":"Farin","key":"ref12"},{"volume-title":"The NURBS Book","year":"1996","author":"Piegl","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11812715_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3739-z"},{"journal-title":"MuZero with self-competition for rate control in VP9 video compression","year":"2022","author":"Mandhane","key":"ref16"},{"issue":"268","key":"ref17","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning im-plementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research. JMLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IECON49645.2022.9968893"}],"event":{"name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2023,10,1]]},"location":"Honolulu, Oahu, HI, USA","end":{"date-parts":[[2023,10,4]]}},"container-title":["2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10391856\/10393862\/10394648.pdf?arnumber=10394648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:18:19Z","timestamp":1706793499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10394648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/smc53992.2023.10394648","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}