{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:08:34Z","timestamp":1768273714907,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852326","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Carlo","family":"D'Eramo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Cini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref33","first-page":"943","article-title":"A bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143955"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.874"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"222","DOI":"10.7551\/mitpress\/3115.003.0030","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"1991","journal-title":"International Conference on Simulation of Adaptive Behavior From Animals to Animats"},{"key":"ref37","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","volume":"16","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref35","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref10","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"150","article-title":"Model based bayesian exploration","author":"dearden","year":"1999","journal-title":"Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref13","first-page":"761","article-title":"Bayesian q-learning","author":"dearden","year":"1998","journal-title":"AAAI"},{"key":"ref14","first-page":"1032","article-title":"Estimating maximum expected value through gaussian approximation","author":"d\u2019eramo","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015204"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1108\/17563781011049179"},{"key":"ref17","article-title":"Double q-learning","author":"v hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref19","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","first-page":"2377","article-title":"Generalization and exploration via randomized value functions","author":"osband","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"3003","article-title":"(more) efficient reinforcement learning via posterior sampling","author":"osband","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"56","article-title":"Logarithmic online regret bounds for undiscounted reinforcement learning","volume":"49","author":"auer","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"355","article-title":"Self-development framework for reinforcement learning agents","volume":"178","author":"bonarini","year":"2006","journal-title":"International Conference on Development and Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref8","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref7","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref9","author":"d\u2019eramo","year":"2019","journal-title":"Mushroom RL python library"},{"key":"ref1","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","author":"asadi","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref20","article-title":"On the sample complexity of reinforcement learning","author":"kakade","year":"2003","journal-title":"PhD thesis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref24","article-title":"Simulation studies in optimistic bayesian sampling in contextual-bandit problems","volume":"11","author":"may","year":"2011","journal-title":"Statistics Group Department of Mathematics University of Bristol"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref26","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","location":"Budapest, Hungary","start":{"date-parts":[[2019,7,14]]},"end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852326.pdf?arnumber=8852326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T08:54:15Z","timestamp":1721811255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852326","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}