{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T00:57:08Z","timestamp":1789779428150,"version":"4.0.1"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460633","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"5090-5096","source":"Crossref","is-referenced-by-count":1,"title":["Eager and Memory-Based Non-Parametric Stochastic Search Methods for Learning Control"],"prefix":"10.1109","author":[{"given":"Victor","family":"Barbaros","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Herke","family":"van Hoof","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abbas","family":"Abdolmaleki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Megerl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"438","article-title":"Efficient memory-based dynamic programming","author":"peng","year":"1995","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref38","article-title":"Reinforcement learning with high-dimensional continuous actions","author":"baird","year":"1993","journal-title":"Wright Laboratory Wright-Patterson Air Force Base Tech Rep WL-TR-93–1147"},{"key":"ref33","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref32","article-title":"Path integral control by reproducing kernel Hilbert space embedding","author":"rawlik","year":"2013","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref31","article-title":"Policy search in reproducing kernel Hilbert space","author":"vien","year":"2016","journal-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref30","article-title":"Policy search in reproducing kernel Hilbert space","author":"bagnell","year":"2003","journal-title":"CMU Tech Rep RI–TR-03–45"},{"key":"ref37","first-page":"471","article-title":"Scaling up average reward reinforcement learning by approximating the domain models and the value function","author":"tadepalli","year":"1996","journal-title":"International Conference on Machine Learning"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-2660-4_33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"ref34","first-page":"1","article-title":"Non-parametric policy search with limited information loss","volume":"18","author":"van hoof","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","volume":"1","author":"rasmussen","year":"2006","journal-title":"Gaussian processes for machine learning the mit press"},{"key":"ref40","first-page":"903","article-title":"Practical reinforcement learning in continuous spaces","author":"smart","year":"2000","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref11","article-title":"Learning parameterized skills","author":"da silva","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","article-title":"Learning compact parameterized skills with a single regression","author":"stulp","year":"2013","journal-title":"IEEE-RAS International Conference on Humanoid Robots (Humanoids)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10911","article-title":"Policy search with high-dimensional context variables","author":"tangkaratt","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2643","DOI":"10.1109\/IROS.2016.7759411","article-title":"Non-parametric contextual stochastic search","author":"abdolmaleki","year":"2016","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"Proceedings of the 24th National Conference on Artificial Intelligence (AAAI)"},{"key":"ref17","article-title":"Model Based Relative Entropy Stochastic Search","author":"abdolmaleki","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref19","first-page":"535","article-title":"Modelling transition dynamics in MDPs with RKHS embeddings","author":"gr\u00fcncw\u00e4lder","year":"2012","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref28","first-page":"2650","article-title":"Reinforcement learning to adjust robot movements to new situations","author":"kober","year":"2011","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref4","article-title":"Path Integral Policy Improvement with Covariance Matrix Adaptation","author":"stulp","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1609\/aaai.v25i1.7930","article-title":"Non-parametric approximate linear programming for MDPs","author":"pazis","year":"2011","journal-title":"Proceedings of the National Conference on Artificial Intelligence (AAAI)"},{"key":"ref3","article-title":"Efficient Natural Evolution Strategies","author":"sun","year":"0","journal-title":"Proceedings of the Annual Conference on Genetic and Evolutionary Computation (GECCO)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2908961.2909012"},{"key":"ref29","first-page":"590","article-title":"Modelling policies in MDPs in reproducing kernel Hilbert space","author":"lever","year":"2015","journal-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.005"},{"key":"ref8","article-title":"Evolutionary optimization for parameterized whole-body dynamic motor skills","author":"ha","year":"2016","journal-title":"Proceedings of IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref7","first-page":"3190","article-title":"Hierarchical relative entropy policy search","volume":"17","author":"daniel","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref2","article-title":"State-dependent Exploration for Policy Gradient Methods","author":"r\u00fcckstie?","year":"2008","journal-title":"Proceedings of the European Conference on Machine Learning (ECML)"},{"key":"ref9","first-page":"958","article-title":"Using locally weighted regression for robot learning","author":"atkeson","year":"1991","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref1","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref22","first-page":"1719","article-title":"A non-parametric approach to dynamic programming","author":"kroemer","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553504"},{"key":"ref42","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368208"},{"key":"ref41","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","first-page":"154","article-title":"Bayes meets Bellman: The Gaussian process approach to temporal difference learning","volume":"20","author":"engel","year":"2003","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref26","first-page":"1","article-title":"Gaussian processes in reinforcement learning","volume":"4","author":"rasmussen","year":"2003","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"}],"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\/08460633.pdf?arnumber=8460633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T18:18:30Z","timestamp":1751998710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460633","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}