Unifying PAC and regret: Uniform PAC bounds for episodic reinforcement learning C Dann, T Lattimore, E Brunskill Advances in Neural Information Processing Systems, 5717-5727, 2017 | 306 | 2017 |
Policy evaluation with temporal differences: a survey and comparison. C Dann, G Neumann, J Peters Journal of Machine Learning Research 15 (1), 809-883, 2014 | 274 | 2014 |
Sample complexity of episodic fixed-horizon reinforcement learning C Dann, E Brunskill Advances in Neural Information Processing Systems, 2818-2826, 2015 | 262 | 2015 |
Scaling up behavioral science interventions in online education RF Kizilcec, J Reich, M Yeomans, C Dann, E Brunskill, G Lopez, S Turkay, ... Proceedings of the National Academy of Sciences, 2020 | 167 | 2020 |
Policy certificates: Towards accountable reinforcement learning C Dann, L Li, W Wei, E Brunskill International Conference on Machine Learning, 1507-1516, 2019 | 157 | 2019 |
On Oracle-Efficient PAC RL with Rich Observations C Dann, N Jiang, A Krishnamurthy, A Agarwal, J Langford, RE Schapire Advances in Neural Information Processing Systems, 1429-1439, 2018 | 116 | 2018 |
Thoughts on massively scalable Gaussian processes AG Wilson, C Dann, H Nickisch arXiv preprint arXiv:1511.01870, 2015 | 113 | 2015 |
RLPy: a value-function-based reinforcement learning framework for education and research. A Geramifard, C Dann, RH Klein, W Dabney, JP How Journal of Machine Learning Research 16, 1573-1578, 2015 | 105* | 2015 |
Being optimistic to be conservative: Quickly learning a cvar policy R Keramati, C Dann, A Tamkin, E Brunskill Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 4436-4443, 2020 | 82 | 2020 |
The human kernel AG Wilson, C Dann, C Lucas, EP Xing Advances in Neural Information Processing Systems, 2854-2862, 2015 | 80 | 2015 |
Automated matching of pipeline corrosion features from in-line inspection data MR Dann, C Dann Reliability Engineering & System Safety 162, 40-50, 2017 | 51 | 2017 |
Regret Bound Balancing and Elimination for Model Selection in Bandits and RL A Pacchiano, C Dann, C Gentile, P Bartlett arXiv preprint arXiv:2012.13045, 2020 | 44 | 2020 |
A Model Selection Approach for Corruption Robust Reinforcement Learning CY Wei, C Dann, J Zimmert International Conference on Algorithmic Learning Theory, 2022 | 43 | 2022 |
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning C Dann, M Mohri, T Zhang, J Zimmert Advances in Neural Information Processing Systems 34, 2021 | 41* | 2021 |
Bayesian time-of-flight for realtime shape, illumination and albedo A Adam, C Dann, O Yair, S Mazor, S Nowozin IEEE transactions on pattern analysis and machine intelligence 39 (5), 851-864, 2017 | 40 | 2017 |
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation C Dann, Y Mansour, M Mohri, A Sekhari, K Sridharan International Conference on Machine Learning, 4666-4689, 2022 | 39 | 2022 |
Dynamic balancing for model selection in bandits and rl A Cutkosky, C Dann, A Das, C Gentile, A Pacchiano, M Purohit International Conference on Machine Learning, 2276-2285, 2021 | 35 | 2021 |
Distributionally-aware exploration for cvar bandits A Tamkin, R Keramati, C Dann, E Brunskill NeurIPS 2019 Workshop on Safety and Robustness on Decision Making, 2019 | 35 | 2019 |
Beyond value-function gaps: Improved instance-dependent regret bounds for episodic reinforcement learning C Dann, TV Marinov, M Mohri, J Zimmert Advances in Neural Information Processing Systems 34, 2021 | 29 | 2021 |
Energetic natural gradient descent P Thomas, BC Silva, C Dann, E Brunskill International Conference on Machine Learning, 2887-2895, 2016 | 23 | 2016 |