| Deep exploration via bootstrapped DQN I Osband, C Blundell, A Pritzel, B Van Roy Advances in neural information processing systems, 4026-4034, 2016 | 633 | 2016 |
| Deep q-learning from demonstrations T Hester, M Vecerik, O Pietquin, M Lanctot, T Schaul, B Piot, D Horgan, ... Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 403 | 2018 |
| Noisy networks for exploration M Fortunato, MG Azar, B Piot, J Menick, I Osband, A Graves, V Mnih, ... arXiv preprint arXiv:1706.10295, 2017 | 394 | 2017 |
| A tutorial on thompson sampling D Russo, B Van Roy, A Kazerouni, I Osband, Z Wen arXiv preprint arXiv:1707.02038, 2017 | 316 | 2017 |
| Minimax regret bounds for reinforcement learning MG Azar, I Osband, R Munos arXiv preprint arXiv:1703.05449, 2017 | 232 | 2017 |
| Generalization and exploration via randomized value functions I Osband, B Van Roy, Z Wen International Conference on Machine Learning, 2377-2386, 2016 | 180 | 2016 |
| Learning from demonstrations for real world reinforcement learning T Hester, M Vecerik, O Pietquin, M Lanctot, T Schaul, B Piot, A Sendonaris, ... | 127 | 2017 |
| Randomized prior functions for deep reinforcement learning I Osband, J Aslanides, A Cassirer Advances in Neural Information Processing Systems, 8617-8629, 2018 | 125 | 2018 |
| Deep Exploration via Randomized Value Functions I Osband https://searchworks.stanford.edu/view/11891201, 2016 | 117 | 2016 |
| Why is posterior sampling better than optimism for reinforcement learning? I Osband, B Van Roy International Conference on Machine Learning, 2701-2710, 2017 | 111 | 2017 |
| Deep learning for time series modeling E Busseti, I Osband, S Wong Technical report, Stanford University, 1-5, 2012 | 97 | 2012 |
| The uncertainty bellman equation and exploration B O’Donoghue, I Osband, R Munos, V Mnih International Conference on Machine Learning, 3836-3845, 2018 | 72 | 2018 |
| Model-based reinforcement learning and the eluder dimension I Osband, B Van Roy Advances in Neural Information Processing Systems 27, 1466-1474, 2014 | 65 | 2014 |
| Near-optimal reinforcement learning in factored mdps I Osband, B Van Roy Advances in Neural Information Processing Systems 27, 604-612, 2014 | 59 | 2014 |
| Risk versus Uncertainty in Deep Learning: Bayes, Bootstrap and the Dangers of Dropout I Osband http://bayesiandeeplearning.org/papers/BDL_4.pdf, 0 | 57* | |
| On lower bounds for regret in reinforcement learning I Osband, B Van Roy arXiv preprint arXiv:1608.02732, 2016 | 51 | 2016 |
| Bootstrapped thompson sampling and deep exploration I Osband, B Van Roy arXiv preprint arXiv:1507.00300, 2015 | 49 | 2015 |
| Behaviour suite for reinforcement learning I Osband, Y Doron, M Hessel, J Aslanides, E Sezener, A Saraiva, ... arXiv preprint arXiv:1908.03568, 2019 | 41 | 2019 |
| (More) efficient reinforcement learning via posterior sampling I Osband, D Russo, B Van Roy Advances in Neural Information Processing Systems 26, 3003-3011, 2013 | 34 | 2013 |
| Meta-learning of sequential strategies PA Ortega, JX Wang, M Rowland, T Genewein, Z Kurth-Nelson, ... arXiv preprint arXiv:1905.03030, 2019 | 28 | 2019 |
Benjamin Van RoyStanford UniversityVerified email at stanford.edu
