{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:57:39Z","timestamp":1729637859158,"version":"3.28.0"},"reference-count":43,"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.2019.8851736","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":1,"title":["Exploration Driven by an Optimistic Bellman Equation"],"prefix":"10.1109","author":[{"given":"Samuele","family":"Tosatto","sequence":"first","affiliation":[]},{"given":"Carlo","family":"D'Eramo","sequence":"additional","affiliation":[]},{"given":"Joni","family":"Pajarinen","sequence":"additional","affiliation":[]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"key":"ref38","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"In International Conference on Machine Learning"},{"key":"ref31","first-page":"48","article-title":"Driven by compression progress: A simple principle explains essential aspects of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes","author":"schmidhuber","year":"2008","journal-title":"Anticipatory Behavior in Adaptive Learning Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0393-3"},{"key":"ref37","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref36","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"943","article-title":"A Bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"In ICML"},{"key":"ref34","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"singh","year":"2004","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"1332","article-title":"Sample efficient reinforcement learning with gaussian processes","author":"grande","year":"2014","journal-title":"International Conference on Machine Learning"},{"journal-title":"Technical Report “Exploration Driven by an Optimistic Bellman Equation”","year":"2018","author":"tosatto","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref13","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","author":"jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4120-1_14"},{"key":"ref18","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001","journal-title":"Institute of Systems and Robotics Tech Rep"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007541107674"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref4","first-page":"213?231","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":"ref27","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"arXiv preprint arXiv 1703 01310"},{"key":"ref3","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":"ref6","article-title":"UCB and InfoGain Exploration via Q-ensembles","author":"chen","year":"2017","journal-title":"arXiv preprint arXiv 1706 01502"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref5","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref7","first-page":"761","article-title":"Bayesian Q-learning","author":"dearden","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503252"},{"key":"ref9","first-page":"1499","article-title":"Convergence of optimistic and incremental Q-learning","author":"even-dar","year":"2002","journal-title":"Advances in neural information processing systems"},{"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","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref22","article-title":"A unified view of entropy-regularized markov decision processes","author":"neu","year":"2017","journal-title":"arXiv preprint arXiv 1705 07798"},{"key":"ref21","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"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.614"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_11"},{"key":"ref23","first-page":"3839","article-title":"The uncertainty Bellman equation and exploration","author":"o\u2019donoghue","year":"2018","journal-title":"Proceedings of 35th International Conference on Machine Learning"},{"key":"ref26","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":"ref43","first-page":"2433","article-title":"Interval estimation for reinforcement-learning algorithms in continuous-state domains","author":"white","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","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\/08851736.pdf?arnumber=8851736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T16:27:12Z","timestamp":1664555232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8851736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8851736","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}