{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T22:20:31Z","timestamp":1762899631254,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8463197","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:28:03Z","timestamp":1537554483000},"page":"7571-7578","source":"Crossref","is-referenced-by-count":17,"title":["Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search"],"prefix":"10.1109","author":[{"given":"Remi","family":"Pautrat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Chatzilygeroudis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Baptiste","family":"Mouret","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Evo-lution of repertoire-based control for robots with complex locomotor systems","author":"duarte","year":"2017","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref33","article-title":"Data-Efficient Control Policy Search using Residual Dynamics Learning","author":"saveriano","year":"2017","journal-title":"Proc of IROS"},{"journal-title":"Gp-ilqg Data-driven robust optimal control for uncertain nonlinear dynamical systems","year":"2017","author":"lee","key":"ref32"},{"key":"ref31","article-title":"Deep Kernels for Optimizing Locomotion Controllers","author":"antonova","year":"2017","journal-title":"Proc of CoRL"},{"key":"ref30","article-title":"Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization","author":"marco","year":"2017","journal-title":"Proc of ICRA"},{"journal-title":"Illuminating search spaces by mapping elites","year":"2015","author":"mouret","key":"ref37"},{"key":"ref36","article-title":"Gaussian process regression for optimization","author":"lizotte","year":"2005","journal-title":"NIPS Workshop on Value of Information"},{"journal-title":"Limbo A fast and flexible library for Bayesian optimization","year":"2016","author":"cully","key":"ref35"},{"journal-title":"Optimal Learning","year":"2012","author":"warren","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"ref40","article-title":"Feature space modeling through surrogate illumination","author":"gaier","year":"2017","journal-title":"Proc of GECCO"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref12","article-title":"Efficient reinforcement learning for robots using informative simulated priors","author":"cutler","year":"2015","journal-title":"Proc of ICRA"},{"key":"ref13","article-title":"Gaussian processes and reinforcement learning for identification and control of an autonomous blimp","author":"ko","year":"2007","journal-title":"Proc of ICRA"},{"key":"ref14","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":"ref15","article-title":"Learning predictive terrain models for legged robot locomotion","author":"plagemann","year":"2008","journal-title":"Proc of IROS"},{"journal-title":"A Brief Survey of Deep Reinforcement Learning","year":"2017","author":"arulkumaran","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref18","article-title":"Policy gradient reinforcement learning for fast quadrupedal locomotion","author":"kohl","year":"2004","journal-title":"Proc of ICRA"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"journal-title":"Soft tensegrity robots","year":"2017","author":"rieffel","key":"ref28"},{"key":"ref4","article-title":"Micro-data learning: The other end of the spectrum","author":"mouret","year":"2016","journal-title":"ERCIM News"},{"key":"ref27","article-title":"Safe controller optimization for quadrotors with gaussian processes","author":"berkenkamp","year":"2016","journal-title":"Proc of ICRA"},{"journal-title":"Reset-free Trial-and-Error Learning for Robot Damage Recovery","year":"2016","author":"chatzilygeroudis","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref29","article-title":"Safety-aware robot damage recovery using constrained bayesian optimization and simulated priors","author":"papaspyros","year":"2016","journal-title":"BayesOpt ‘16 Workshop at NIPS"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref8","article-title":"Automatic Gait Optimization with Gaussian Process Regression","author":"lizotte","year":"2007","journal-title":"Proc of IJCAI"},{"key":"ref7","article-title":"Black-Box Data-efficient Policy Search for Robotics","author":"chatzilygeroudis","year":"2017","journal-title":"Proc of IROS"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1038\/nature14422","article-title":"Robots that can adapt like animals","volume":"521","author":"cully","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-015-9463-9"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3585.001.0001","author":"pfeifer","year":"2006","journal-title":"How the Body Shapes the Way We Think A New View of Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref22"},{"key":"ref21","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc of ICML"},{"key":"ref42","article-title":"Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm","author":"vassiliades","year":"2017","journal-title":"IEEE Trans on Evolutionary Computation"},{"key":"ref24","article-title":"A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","volume":"abs 1012 2599","author":"brochu","year":"2010","journal-title":"CoRR"},{"key":"ref41","article-title":"Deep neural networks are easily fooled: High confidence predictions for unrecognizable images","author":"nguyen","year":"2015","journal-title":"Proc of CVPR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref44","article-title":"Optimization of Gaussian process hyperparameters using Rprop","author":"blum","year":"2013","journal-title":"Proc of ESANN"},{"key":"ref26","article-title":"Entropy search for information-efficient global optimization","volume":"13","author":"hennig","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref43","article-title":"Sferesv2: Evolvin’ in the Multi-Core World","author":"mouret","year":"2010","journal-title":"Proc of CEC"},{"journal-title":"Gaussian Processes for Machine Learning","year":"2006","author":"rasmussen","key":"ref25"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","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\/08463197.pdf?arnumber=8463197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:28:06Z","timestamp":1598210886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8463197","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}