{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:07:50Z","timestamp":1762542470844,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,7]]},"DOI":"10.1109\/ijcnn.2015.7280437","type":"proceedings-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T21:48:02Z","timestamp":1443736082000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Online reinforcement learning by Bayesian inference"],"prefix":"10.1109","author":[{"given":"Zhongpu","family":"Xia","sequence":"first","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530856"},{"key":"ref12","first-page":"7049","article-title":"Model-free adaptive dynamic programming for optimal control of discrete-time affine nonlinear system","author":"xia","year":"2014","journal-title":"Proceedings of International Federation of Automatic Control World Congress"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref14","article-title":"Kernel-based models for reinforcement learning","author":"jong","year":"2006","journal-title":"ICML Workshop on Kernel Machines and Reinforcement Learning"},{"journal-title":"Gaussian Processes for Machine Learning","year":"2006","author":"rasmussen","key":"ref15"},{"key":"ref16","first-page":"751","article-title":"Gaussian processes in reinforcement learning","author":"rasmussen","year":"2004","journal-title":"Advances in Neural Information Processing Systems 16"},{"journal-title":"Efficient reinforcement learning using gaussian pro-cesses","year":"2010","author":"deisenroth","key":"ref17"},{"key":"ref18","first-page":"601","article-title":"Gaussian processes for sample efficient reinforcement learning with RMAX-like exploration","author":"jung","year":"2010","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2280013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref6","first-page":"346","article-title":"MEC-a near-optimal online reinforcement learning algorithm for continuous deterministic systems","volume":"26","author":"zhao","year":"2014","journal-title":"IEEE Transactions"},{"key":"ref5","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey and comparison","volume":"15","author":"dann","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.09.034"},{"key":"ref7","first-page":"1","article-title":"Model-free optimal control for affine nonlinear systems with convergence analysis","author":"zhao","year":"2014","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2122257"},{"key":"ref20","first-page":"49","article-title":"Least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref22","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.830985"}],"event":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2015,7,12]]},"location":"Killarney, Ireland","end":{"date-parts":[[2015,7,17]]}},"container-title":["2015 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7256526\/7280295\/07280437.pdf?arnumber=7280437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T20:48:49Z","timestamp":1490388529000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7280437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2015.7280437","relation":{},"subject":[],"published":{"date-parts":[[2015,7]]}}}