Cikkek nyilvánosan hozzáférhető megbízással - Masatoshi UeharaTovábbi információ
Valahol hozzáférhető: 16
Double reinforcement learning for efficient off-policy evaluation in markov decision processes
N Kallus, M Uehara
Journal of Machine Learning Research 21 (167), 1-63, 2020
Megbízások: US National Science Foundation
Efficiently breaking the curse of horizon in off-policy evaluation with double reinforcement learning
N Kallus, M Uehara
Operations Research 70 (6), 3282-3302, 2022
Megbízások: US National Science Foundation
Efficient reinforcement learning in block mdps: A model-free representation learning approach
X Zhang, Y Song, M Uehara, M Wang, A Agarwal, W Sun
International Conference on Machine Learning, 26517-26547, 2022
Megbízások: US National Science Foundation, US Department of Defense
Intrinsically efficient, stable, and bounded off-policy evaluation for reinforcement learning
N Kallus, M Uehara
Advances in Neural Information Processing Systems 32, 2019
Megbízások: US National Science Foundation
Statistically efficient off-policy policy gradients
N Kallus, M Uehara
Proceedings of the 37th International Conference on Machine Learning, 5089-5100, 2020
Megbízások: US National Science Foundation
A minimax learning approach to off-policy evaluation in confounded partially observable markov decision processes
C Shi, M Uehara, J Huang, N Jiang
International Conference on Machine Learning, 20057-20094, 2022
Megbízások: US National Science Foundation, UK Engineering and Physical Sciences …
Localized debiased machine learning: Efficient inference on quantile treatment effects and beyond
N Kallus, X Mao, M Uehara
Journal of Machine Learning Research 25 (16), 1-59, 2024
Megbízások: US National Science Foundation, National Natural Science Foundation of China
Provably efficient reinforcement learning in partially observable dynamical systems
M Uehara, A Sekhari, JD Lee, N Kallus, W Sun
Advances in Neural Information Processing Systems 35, 578-592, 2022
Megbízások: US National Science Foundation
Optimal off-policy evaluation from multiple logging policies
N Kallus, Y Saito, M Uehara
International Conference on Machine Learning, 5247-5256, 2021
Megbízások: US National Science Foundation
Fast Rates for the Regret of Offline Reinforcement Learning
Y Hu, N Kallus, M Uehara
Proceedings of Thirty Fourth Conference on Learning Theory (COLT) 134, 2462-2462, 2021
Megbízások: US National Science Foundation
Future-dependent value-based off-policy evaluation in pomdps
M Uehara, H Kiyohara, A Bennett, V Chernozhukov, N Jiang, N Kallus, ...
Advances in neural information processing systems 36, 15991-16008, 2023
Megbízások: US National Science Foundation, UK Engineering and Physical Sciences …
Distributional Offline Policy Evaluation with Predictive Error Guarantees
WS Runzhe Wu, Masatoshi Uehara
Proceedings of the 40th International Conference on Machine Learning, 37685 …, 2023
Megbízások: US National Science Foundation
Offline minimax soft-q-learning under realizability and partial coverage
M Uehara, N Kallus, JD Lee, W Sun
Advances in Neural Information Processing Systems 36, 12797-12809, 2023
Megbízások: US National Science Foundation, US Department of Defense
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies
N Kallus, M Uehara
Advances in Neural Information Processing Systems 33, 2020
Megbízások: US National Science Foundation
Computationally efficient pac rl in pomdps with latent determinism and conditional embeddings
M Uehara, A Sekhari, JD Lee, N Kallus, W Sun
International Conference on Machine Learning, 34615-34641, 2023
Megbízások: US National Science Foundation
Statistical inference with semiparametric nonignorable nonresponse models
M Uehara, D Lee, JK Kim
Scandinavian Journal of Statistics 50 (4), 1795-1817, 2023
Megbízások: US National Science Foundation
A publikációs és a finanszírozási adatokat számítógépes program határozza meg, automatikusan.