{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:49:17Z","timestamp":1729676957042,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1109\/ijcnn.2012.6252509","type":"proceedings-article","created":{"date-parts":[[2012,8,1]],"date-time":"2012-08-01T16:47:51Z","timestamp":1343839671000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement learning with guided policy search using Gaussian processes"],"prefix":"10.1109","author":[{"given":"Hunor S.","family":"Jakab","sequence":"first","affiliation":[]},{"given":"Lehel","family":"Csato","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Gaussian Processes for Machine Learning","year":"2006","author":"rasmussen","key":"19"},{"key":"22","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Advances in Neural Information Processing Systems NIPS"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"16","article-title":"MCMC using Hamiltonian dynamics","author":"neal","year":"2010","journal-title":"Handbook of Markov Chain Monte Carlo"},{"key":"13","first-page":"1531","volume":"2","author":"kakade","year":"2002","journal-title":"A Natural Policy Gradient"},{"key":"14","article-title":"Automatic gait optimisation for quadruped robots","author":"kim","year":"2003","journal-title":"Australasian Conference on Robotics and Automation"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21738-8_29"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"21"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"20","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S0079-6123(06)65027-9","article-title":"Dynamics systems vs. optimal control - A unifying view","volume":"165","author":"schaal","year":"2007","journal-title":"Progress in Brain Research"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"journal-title":"Fitted q-iteration in Continuous Action-space MDPs","year":"2007","author":"antos","key":"1"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.846489"},{"key":"7","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317250933"},{"journal-title":"Gaussian Processes - Iterative Sparse Approximation","year":"2002","author":"csato?","key":"5"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-33656-5_4"},{"key":"9","first-page":"457","article-title":"Bayesian policy gradient algorithms","volume":"19","author":"ghavamzadeh","year":"2007","journal-title":"Advances in Neural Information Processing Systems NIPS"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.12.019"}],"event":{"name":"2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane)","start":{"date-parts":[[2012,6,10]]},"location":"Brisbane, Australia","end":{"date-parts":[[2012,6,15]]}},"container-title":["The 2012 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6241467\/6252360\/06252509.pdf?arnumber=6252509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T00:01:47Z","timestamp":1643068907000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6252509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2012.6252509","relation":{},"subject":[],"published":{"date-parts":[[2012,6]]}}}