{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:36:14Z","timestamp":1793824574681,"version":"4.6.1"},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/ita.2018.8503252","type":"proceedings-article","created":{"date-parts":[[2018,10,25]],"date-time":"2018-10-25T19:42:52Z","timestamp":1540496572000},"page":"1-9","source":"Crossref","is-referenced-by-count":52,"title":["Efficient Exploration Through Bayesian Deep Q-Networks"],"prefix":"10.1109","author":[{"given":"Kamyar","family":"Azizzadenesheli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Brunskill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animashree","family":"Anandkumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref38","article-title":"Shallow updates for deep reinforcement learning","author":"levine","year":"2017"},{"key":"ref33","article-title":"Generalization and exploration via randomized value functions","author":"osband","year":"2014","journal-title":"ArXiv"},{"key":"ref32","article-title":"Deep exploration via randomized value functions","author":"osband","year":"2017","journal-title":"ArXiv"},{"key":"ref31","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"ArXiv"},{"key":"ref30","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref37","article-title":"Scalable bayesian optimization using deep neural networks","author":"snoek","year":"2015","journal-title":"ICML"},{"key":"ref36","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017"},{"key":"ref35","article-title":"Efficient exploration for dialogue policy learning with bbq networks & replay buffer spiking","author":"lipton","year":"2016"},{"key":"ref34","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Reinforcement learning in rich-observation mdps using spectral methods","author":"azizzadenesheli","year":"2016"},{"key":"ref27","article-title":"Exploratory gradient boosting for reinforcement learning in complex domains","author":"abel","year":"2016","journal-title":"ArXiv"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref2","article-title":"Exploration:a study of count-based exploration for deep reinforcement learning","author":"tang","year":"2016","journal-title":"ArXiv"},{"key":"ref1","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":"ref20","first-page":"2773","article-title":"Tensor decompositions for learning latent variable models","volume":"15","author":"anandkumar","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref22","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0663"},{"key":"ref24","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"2012","journal-title":"COLT"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0650"},{"key":"ref26","first-page":"1","article-title":"Bayesian optimal control of smoothly parameterized systems","author":"abbasi-","year":"2015","journal-title":"UAI"},{"key":"ref25","article-title":"(more) efficient reinforcement learning via posterior sampling","author":"osband","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref50","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"key":"ref51","article-title":"A unified view of entropy-regularized markov decision processes","author":"neu","year":"2017","journal-title":"ArXiv"},{"key":"ref52","article-title":"Equivalence between policy gradients and soft q-learning","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref10","article-title":"Revisiting the arcade learning environment: Evaluation protocols and open problems for general agents","author":"machado","year":"2017"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref40","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"ArXiv"},{"key":"ref13","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"ArXiv"},{"key":"ref14","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref15","article-title":"Combating reinforcement learning's sisyphean curse with intrinsic fear","author":"lipton","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref17","article-title":"A bayesian sampling approach to exploration in reinforcement learning","author":"asmuth","year":"2009","journal-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref18","article-title":"Near-optimal regret bounds for reinforcement learning","author":"jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","article-title":"Reinforcement learning of pomdps using spectral methods","author":"azizzadenesheli","year":"2016","journal-title":"Proceedings of the Annual Conference on Learning Theory (COLT)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref3","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1561\/2200000049","article-title":"Bayesian reinforcement learning: A survey","author":"ghavamzadeh","year":"2015","journal-title":"Foundations and Trends\ufffd in Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2016.10.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","article-title":"A bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"ICML"},{"key":"ref49","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref46","first-page":"127","article-title":"Thompson sampling for contextual bandits with linear payoffs","author":"agrawal","year":"2013","journal-title":"ICML"},{"key":"ref45","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"ArXiv"},{"key":"ref48","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Linear thompson sampling revisited","author":"abeille","year":"2017","journal-title":"AISTATS 2017–20th International Conference on Artificial Intelligence and Statistics"},{"key":"ref42","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref44","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref43","volume":"1","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"}],"event":{"name":"2018 Information Theory and Applications Workshop (ITA)","location":"San Diego, CA","start":{"date-parts":[[2018,2,11]]},"end":{"date-parts":[[2018,2,16]]}},"container-title":["2018 Information Theory and Applications Workshop (ITA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8486613\/8502949\/08503252.pdf?arnumber=8503252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:52:14Z","timestamp":1775253134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8503252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/ita.2018.8503252","relation":{},"subject":[],"published":{"date-parts":[[2018,2]]}}}