{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T01:46:19Z","timestamp":1747791979414,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"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":[[2024,7,10]]},"DOI":"10.23919\/acc60939.2024.10644690","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:19Z","timestamp":1725558979000},"page":"104-110","source":"Crossref","is-referenced-by-count":1,"title":["Data-Efficient Uncertainty-Guided Model-Based Reinforcement Learning with Unscented Kalman Bayesian Neural Networks"],"prefix":"10.23919","author":[{"given":"Xinyang","family":"Wu","sequence":"first","affiliation":[{"name":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"}]},{"given":"Elisabeth","family":"Wedernikow","sequence":"additional","affiliation":[{"name":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"}]},{"given":"Marco F.","family":"Huber","sequence":"additional","affiliation":[{"name":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"}]}],"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":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186787"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196924"},{"key":"ref7","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160686"},{"key":"ref10","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on machine learning (ICML-11)","author":"Deisenroth","year":"2011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21021-6"},{"key":"ref12","article-title":"Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting","volume":"15","author":"Girard","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"10069","article-title":"Kalman bayesian neural networks for closed-form online learning","volume-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","volume":"37","author":"Wagner","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010608"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref17","article-title":"Stochastic variational inference","author":"Hoffman","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"ref20","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","volume-title":"International conference on artificial intelligence and statistics. PMLR","author":"Kamthe","year":"2018"},{"issue":"34","key":"ref22","first-page":"25","article-title":"Improving pilco with bayesian neural network dynamics models","volume-title":"Data-efficient machine learning workshop, ICML","volume":"4","author":"Gal","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/drones7040228"},{"key":"ref24","first-page":"1","article-title":"Tractable Approximate Gaussian Inference for Bayesian Neural Networks","volume":"22","author":"Goulet","year":"2021","journal-title":"Journal of Ma-chine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303764"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1117\/12.280797"},{"journal-title":"Quadratic forms in random variables","year":"1992","author":"Mathai","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"}],"event":{"name":"2024 American Control Conference (ACC)","start":{"date-parts":[[2024,7,10]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644130\/10644150\/10644690.pdf?arnumber=10644690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:12:59Z","timestamp":1725693179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/acc60939.2024.10644690","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]}}}