{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:15:19Z","timestamp":1729649719874,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,7]]},"DOI":"10.1109\/ijcnn.2015.7280824","type":"proceedings-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T21:48:02Z","timestamp":1443736082000},"page":"1-7","source":"Crossref","is-referenced-by-count":30,"title":["Faster reinforcement learning after pretraining deep networks to predict state dynamics"],"prefix":"10.1109","author":[{"given":"Charles W.","family":"Anderson","sequence":"first","affiliation":[]},{"given":"Minwoo","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Daniel L.","family":"Elliott","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/11564096_32","article-title":"Neural fitted q iteration-first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"2005","journal-title":"Mechine Learning ECML 2005 ser Lecture Notes in Artificial Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80056-5"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010640"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"year":"0","key":"ref18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010612"},{"key":"ref3","article-title":"Convergent temporal-difference learning with arbitrary smooth function approximation","volume":"22","author":"maei","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the Triternational Conference on Machine Learning (ICML 2011)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-934613-41-5.50014-3"},{"article-title":"Learning and problem solving with multilayered connectionist systems","year":"1986","author":"anderson","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-036-2.50088-6"}],"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\/07280824.pdf?arnumber=7280824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T20:36:48Z","timestamp":1498250208000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7280824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2015.7280824","relation":{},"subject":[],"published":{"date-parts":[[2015,7]]}}}