{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:19:39Z","timestamp":1783653579234,"version":"3.55.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/icra.2017.7989186","type":"proceedings-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T21:44:28Z","timestamp":1501019068000},"page":"1557-1563","source":"Crossref","is-referenced-by-count":74,"title":["Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization"],"prefix":"10.1109","author":[{"given":"Alonso","family":"Marco","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Berkenkamp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Hennig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela P.","family":"Schoellig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Krause","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bayesian Approach to Global Optimization, ser","volume":"37","author":"mockus","year":"1989","journal-title":"Mathematics and Its Applications"},{"key":"ref11","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref12","first-page":"944","article-title":"Auto-matic gait optimization with Gaussian process regression","volume":"7","author":"lizotte","year":"2007","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095076"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2016.7810598"},{"key":"ref16","author":"berkenkamp","year":"2016","journal-title":"Bayesian optimization with safety constraints Safe and automatic parameter tuning in robotics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907117"},{"key":"ref18","first-page":"2447","article-title":"Contextual Gaussian process bandit optimization","author":"krause","year":"2011","journal-title":"Neural Information Processing Systems"},{"key":"ref19","first-page":"2004","article-title":"Multi-Task Bayesian Optimization","author":"swersky","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref28","author":"anderson","year":"2007","journal-title":"Optimal Control Linear Quadratic Methods"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-008-9354-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.01455"},{"key":"ref3","first-page":"1809","article-title":"Entropy search for information-efficient global optimization","volume":"13","author":"hennig","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967370"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2419431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143845"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.1.1"},{"key":"ref22","author":"kandasamy","year":"2016","journal-title":"Multi-fidelity Gaussian process bandit optimisation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2007.1900"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0314"},{"key":"ref23","author":"poloczek","year":"2016","journal-title":"Multi-Information Source Optimization with General Model Discrepancies"},{"key":"ref26","year":"0","journal-title":"Selferecting single inverted pendulum — Instructor manual"},{"key":"ref25","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"srinivas","year":"2010","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","location":"Singapore, Singapore","start":{"date-parts":[[2017,5,29]]},"end":{"date-parts":[[2017,6,3]]}},"container-title":["2017 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7960754\/7988677\/07989186.pdf?arnumber=7989186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,16]],"date-time":"2017-08-16T15:41:50Z","timestamp":1502898110000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7989186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra.2017.7989186","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}