{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T04:19:59Z","timestamp":1725423599558},"reference-count":8,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/nabic.2010.5716276","type":"proceedings-article","created":{"date-parts":[[2011,2,18]],"date-time":"2011-02-18T14:03:54Z","timestamp":1298037834000},"page":"215-220","source":"Crossref","is-referenced-by-count":1,"title":["Supervised reinforcement learning in discrete environment domains"],"prefix":"10.1109","author":[{"given":"B","family":"Jensen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D","family":"Ortiz-Arroyo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N","family":"Cruz-Corte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F","family":"Rodri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/09548980500361624"},{"key":"ref3","article-title":"Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning)","author":"sutton","year":"1998","journal-title":"The MIT Press"},{"key":"ref6","first-page":"596","article-title":"Two kinds of training information for evaluation function learning","author":"utgoff","year":"1991","journal-title":"Proceedings of the Ninth Annual Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00110-2"},{"journal-title":"Biped dynamic walking using reinforcement learning","year":"1996","author":"benbrahim","key":"ref8"},{"key":"ref7","article-title":"Supervised actor-critic reinforcement learning","author":"rosenstein","year":"2004","journal-title":"Learning and Approximate Dynamic Programming Scaling up to the Real World"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref1","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","author":"crites","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"}],"event":{"name":"2010 Second World Congress on Nature and Biologically Inspired Computing (NaBIC 2010)","start":{"date-parts":[[2010,12,15]]},"location":"Fukuoka","end":{"date-parts":[[2010,12,17]]}},"container-title":["2010 Second World Congress on Nature and Biologically Inspired Computing (NaBIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5710537\/5716265\/05716276.pdf?arnumber=5716276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T03:03:16Z","timestamp":1490065396000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5716276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/nabic.2010.5716276","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}