{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:09:09Z","timestamp":1771949349598,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967630","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"2868-2875","source":"Crossref","is-referenced-by-count":16,"title":["Reinforcement Learning Boat Autopilot: A Sample-efficient and Model Predictive Control based Approach"],"prefix":"10.1109","author":[{"given":"Yunduan","family":"Cui","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigeki","family":"Osaki","sequence":"additional","affiliation":[{"name":"FURUNO ELECTRIC CO., LTD.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2002.806465"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-014-0057-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2011.2181513"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref14","volume":"1","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref15","first-page":"2319","article-title":"Bayesian policy gradient and actor-critic algorithms","volume":"17","author":"ghavamzadeh","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","article-title":"Sparse gaussian process temporal difference learning for marine robot navigation","author":"martin","year":"2018","journal-title":"CoRL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0549-y"},{"key":"ref19","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"kamthe","year":"2018","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2206473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2016.04.018"},{"key":"ref7","first-page":"2899","article-title":"Reinforcement learning with autonomous small unmanned aerial vehicles in cluttered environments","author":"tran","year":"2015","journal-title":"AIAA Aviation Technology Integration and Operations Conference"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2011.09.012"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2015.04.003"},{"key":"ref20","author":"mackay","year":"2003","journal-title":"Information Theory Inference and Learning Algorithms"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553403"},{"key":"ref21","first-page":"545","article-title":"Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting","author":"girard","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-40065-5_18"},{"key":"ref26","first-page":"25","article-title":"Efficient multioutput gaussian processes through variational inducing kernels","author":"\u00e1lvarez","year":"2010","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref25","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","author":"snelson","year":"2006","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967630.pdf?arnumber=8967630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:54Z","timestamp":1755800634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967630","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}