{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:20:30Z","timestamp":1774628430790,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"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":[[2021,10,31]]},"DOI":"10.1109\/ieeeconf53345.2021.9723135","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T15:26:46Z","timestamp":1646407606000},"page":"1018-1022","source":"Crossref","is-referenced-by-count":5,"title":["On-Policy Reinforcement Learning via Ensemble Gaussian Processes with Application to Resource Allocation"],"prefix":"10.1109","author":[{"given":"Konstantinos D.","family":"Polyzos","sequence":"first","affiliation":[{"name":"University of Minnesota,Dept. of ECE,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Minnesota,Dept. of ECE,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alireza","family":"Sadeghi","sequence":"additional","affiliation":[{"name":"University of Minnesota,Dept. of ECE,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios B.","family":"Giannakis","sequence":"additional","affiliation":[{"name":"University of Minnesota,Dept. of ECE,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414667"},{"key":"ref11","author":"lu","year":"2021","journal-title":"Robust and adaptive temporal-difference learning using an ensemble of Gaussian processes"},{"key":"ref12","author":"lu","year":"2021","journal-title":"Incremental ensemble Gaussian processes"},{"key":"ref13","article-title":"Ensemble Gaussian processes with spectral features for online interactive learning with scalability","author":"lu","year":"2020","journal-title":"AISTATS"},{"key":"ref14","first-page":"179","article-title":"Sparse gptd learning for marine robot navigation","author":"martin","year":"2018","journal-title":"ICRL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3122095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413970"},{"key":"ref18","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref19","first-page":"1177","article-title":"Random features for large-scale kernel machines","author":"rahimi","year":"2008","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref3","first-page":"465","article-title":"PILCO: A model- based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref5","first-page":"154","article-title":"Bayes meets Bellman: The Gaussian process approach to temporal difference learning","author":"engel","year":"2003","journal-title":"ICML"},{"key":"ref8","article-title":"Inverse reinforcement learning via deep Gaussian process","author":"jin","year":"2017","journal-title":"UAI"},{"key":"ref7","first-page":"1332","article-title":"Sample efficient reinforcement learning with Gaussian processes","author":"grande","year":"2014","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2896243"},{"key":"ref9","first-page":"751758","article-title":"Gaussian processes in reinforcement learning","author":"kuss","year":"2004","journal-title":"NeurIPS"},{"key":"ref1","first-page":"2249","article-title":"An empirical evaluation of Thompson sampling","volume":"24","author":"chapelle","year":"2011"},{"key":"ref20","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0650"},{"key":"ref21","volume":"37","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2936193"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2787979"},{"key":"ref26","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref25","first-page":"642","article-title":"Meta reinforcement learning with latent variable Gaussian processes","volume":"34","author":"s\u00e6mundsson","year":"2018","journal-title":"UAI"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2021,10,31]]},"end":{"date-parts":[[2021,11,3]]}},"container-title":["2021 55th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9723034\/9723086\/09723135.pdf?arnumber=9723135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T17:20:14Z","timestamp":1655745614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723135","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}