Active learning for identification of linear dynamical systems A Wagenmaker, K Jamieson Conference on Learning Theory, 3487-3582, 2020 | 53 | 2020 |
Reward-free rl is no harder than reward-aware rl in linear markov decision processes AJ Wagenmaker, Y Chen, M Simchowitz, S Du, K Jamieson International Conference on Machine Learning, 22430-22456, 2022 | 52 | 2022 |
Leveraging offline data in online reinforcement learning A Wagenmaker, A Pacchiano International Conference on Machine Learning, 35300-35338, 2023 | 31 | 2023 |
Beyond no regret: Instance-dependent pac reinforcement learning AJ Wagenmaker, M Simchowitz, K Jamieson Conference on Learning Theory, 358-418, 2022 | 30 | 2022 |
First-order regret in reinforcement learning with linear function approximation: A robust estimation approach AJ Wagenmaker, Y Chen, M Simchowitz, S Du, K Jamieson International Conference on Machine Learning, 22384-22429, 2022 | 29 | 2022 |
Instance-dependent near-optimal policy identification in linear mdps via online experiment design A Wagenmaker, KG Jamieson Advances in Neural Information Processing Systems 35, 5968-5981, 2022 | 26 | 2022 |
Best arm identification with safety constraints Z Wang, AJ Wagenmaker, K Jamieson International Conference on Artificial Intelligence and Statistics, 9114-9146, 2022 | 19 | 2022 |
Task-optimal exploration in linear dynamical systems AJ Wagenmaker, M Simchowitz, K Jamieson International Conference on Machine Learning, 10641-10652, 2021 | 16 | 2021 |
Experimental design for regret minimization in linear bandits A Wagenmaker, J Katz-Samuels, K Jamieson International Conference on Artificial Intelligence and Statistics, 3088-3096, 2021 | 15 | 2021 |
Instance-optimality in interactive decision making: Toward a non-asymptotic theory AJ Wagenmaker, DJ Foster The Thirty Sixth Annual Conference on Learning Theory, 1322-1472, 2023 | 10 | 2023 |
Active learning with safety constraints R Camilleri, A Wagenmaker, JH Morgenstern, L Jain, KG Jamieson Advances in Neural Information Processing Systems 35, 33201-33214, 2022 | 9 | 2022 |
Optimal exploration for model-based rl in nonlinear systems A Wagenmaker, G Shi, KG Jamieson Advances in Neural Information Processing Systems 36, 2024 | 6 | 2024 |
Robust photometric stereo via dictionary learning AJ Wagenmaker, BE Moore, RR Nadakuditi IEEE Transactions on Computational Imaging 5 (2), 212-227, 2018 | 4 | 2018 |
Robust photometric stereo using learned image and gradient dictionaries AJ Wagenmaker, BE Moore, RR Nadakuditi 2017 IEEE International Conference on Image Processing (ICIP), 1457-1461, 2017 | 3 | 2017 |
A bisimulation-like algorithm for abstracting control systems AJ Wagenmaker, N Ozay 2016 54th Annual Allerton Conference on Communication, Control, and …, 2016 | 3 | 2016 |
Using deep video frame prediction for training a controller of an autonomous vehicle A Wagenmaker US Patent 10,762,399, 2020 | 2 | 2020 |
Action-conditioned vehicle control A Wagenmaker, GV Puskorius US Patent 10,599,146, 2020 | 2 | 2020 |
Robust surface reconstruction from gradients via adaptive dictionary regularization AJ Wagenmaker, BE Moore, RR Nadakuditi 2017 IEEE International Conference on Image Processing (ICIP), 1002-1006, 2017 | 2 | 2017 |
ASID: Active Exploration for System Identification in Robotic Manipulation M Memmel, A Wagenmaker, C Zhu, P Yin, D Fox, A Gupta arXiv preprint arXiv:2404.12308, 2024 | | 2024 |
Fair Active Learning in Low-Data Regimes R Camilleri, A Wagenmaker, J Morgenstern, L Jain, K Jamieson arXiv preprint arXiv:2312.08559, 2023 | | 2023 |