{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T15:10:03Z","timestamp":1751382603304,"version":"3.41.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/ssci.2017.8280923","type":"proceedings-article","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T21:44:37Z","timestamp":1518039877000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Exploiting structure and uncertainty of Bellman updates in Markov decision processes"],"prefix":"10.1109","author":[{"given":"Davide","family":"Tateo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"D'Eramo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Nuara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Bonarini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2411","article-title":"Speedy q-learning","author":"ghavamzadeh","year":"2011","journal-title":"Proc NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2006.888760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"ref14","first-page":"530","author":"kobayashi","year":"2009","journal-title":"A Meta-learning Method Based on Temporal Difference Error"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652533"},{"key":"ref16","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","author":"crites","year":"1996","journal-title":"Proc NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIC.2008.318"},{"journal-title":"How to discount deep reinforcement learning Towards new dynamic strategies","year":"2015","author":"francois-lavet","key":"ref18"},{"key":"ref19","first-page":"589","author":"even-dar","year":"2001","journal-title":"Learning Rates for Q-Learning"},{"key":"ref4","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1257\/0002828042002697"},{"key":"ref6","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"Proc AAAI"},{"journal-title":"Estimating the maximum expected value an analysis of (nested) cross-validation and the maximum sample average","year":"2013","author":"hasselt","key":"ref5"},{"key":"ref8","first-page":"1032","article-title":"Estimating maximum expected value through gaussian approximation","author":"d'eramo","year":"2016","journal-title":"Proc ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1050.0451"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proc AAAI"}],"event":{"name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2017,11,27]]},"location":"Honolulu, HI","end":{"date-parts":[[2017,12,1]]}},"container-title":["2017 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8267146\/8280782\/08280923.pdf?arnumber=8280923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T14:42:34Z","timestamp":1751380954000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8280923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ssci.2017.8280923","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}