{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:57:04Z","timestamp":1778662624489,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8461182","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"5105-5112","source":"Crossref","is-referenced-by-count":8,"title":["Data-driven Construction of Symbolic Process Models for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Erik","family":"Derner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiri","family":"Kubalik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5220\/0006505200910100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32937-1_33"},{"key":"ref31","first-page":"49","article-title":"A new, node-focused model for genetic programming","author":"jackson","year":"2012","journal-title":"Genetic Programming 15th European Conference EuroGP 2012 Málaga Spain"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(90)90156-C"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"ref10","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907424"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010608"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/11552246_35","article-title":"Autonomous inverted helicopter flight via reinforcement learning","author":"ng","year":"2006","journal-title":"Experimental Robotics IX The 9th International Symposium on Experimental Robotics"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2016.7759581","article-title":"Improved deep reinforcement learning for robotics through distribution-based experience retention","author":"de bruin","year":"2016","journal-title":"Proceedings IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref15","article-title":"Learning continuous control policies by stochastic value gradients","volume":"abs 1510 9142","author":"heess","year":"2015","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.12.107"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.1165893"},{"key":"ref19","first-page":"1","article-title":"Constructing a No-Reference H. 264\/AVC Bitstream-based Video Quality Metric using Genetic Programming-based Symbolic Regression","volume":"99","author":"staelens","year":"2012","journal-title":"Circuits and Systems for Video Technology IEEE Transactions"},{"key":"ref28","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","first-page":"465472","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1016\/j.automatica.2010.02.006","article-title":"Approximate dynamic programming with a fuzzy parameterization","volume":"46","author":"bu?oniu","year":"2010","journal-title":"Automatica"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1007\/978-3-642-27645-3_18","article-title":"Reinforcement learning in robotics: A survey","author":"kober","year":"2012","journal-title":"Reinforcement Learning State-of-the-Art"},{"key":"ref6","first-page":"7","article-title":"Representations for learning control policies","author":"forbes","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn Workshop Develop Represent"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2442233"},{"key":"ref5","first-page":"101","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"kuvayev","year":"1996","journal-title":"Proceedings of the Ninth Yale Workshop on Adaptive and Learning Systems"},{"key":"ref8","first-page":"95:1","article-title":"Model-based function approximation in reinforcement learning","author":"jong","year":"2007","journal-title":"Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems Ser AAMAS '07"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.05.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref1","article-title":"Continuous deep q-learning with model-based acceleration","volume":"abs 1603 748","author":"gu","year":"2016","journal-title":"CoRR"},{"key":"ref20","article-title":"Using Eureqa in a Stock Day-Trading Application","author":"brauer","year":"2012","journal-title":"Cypress Point Technologies LLC"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3067695.3076009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2012.06.036"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2475716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798684"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"4162","DOI":"10.1016\/j.ifacol.2017.08.805","article-title":"Optimal control via reinforcement learning with symbolic policy approximation","volume":"50","author":"kubal\u00edk","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2014.2303783"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08461182.pdf?arnumber=8461182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T02:02:29Z","timestamp":1598234549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8461182","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}