Följ
Yaqi Duan
Yaqi Duan
Verifierad e-postadress på mit.edu - Startsida
Titel
Citeras av
Citeras av
År
Minimax-optimal off-policy evaluation with linear function approximation
Y Duan, M Wang
International Conference on Machine Learning, 2701-2709, 2020
972020
State aggregation learning from Markov transition data
Y Duan, T Ke, M Wang
Advances in Neural Information Processing Systems, 4486-4495, 2019
462019
Risk bounds and Rademacher complexity in batch reinforcement learning
Y Duan, C Jin, Z Li
International Conference on Machine Learning, 2892-2902, 2021
322021
Near-optimal offline reinforcement learning with linear representation: Leveraging variance information with pessimism
M Yin, Y Duan, M Wang, YX Wang
International Conference on Learning Representations, 2022
232022
Sparse feature selection makes batch reinforcement learning more sample efficient
B Hao, Y Duan, T Lattimore, C Szepesvári, M Wang
International Conference on Machine Learning, 4063-4073, 2021
232021
Optimal policy evaluation using kernel-based temporal difference methods
Y Duan, M Wang, MJ Wainwright
arXiv preprint arXiv:2109.12002, 2021
192021
Bootstrapping statistical inference for off-policy evaluation
B Hao, X Ji, Y Duan, H Lu, C Szepesvári, M Wang
arXiv preprint arXiv:2102.03607, 2021
132021
Learning low-dimensional state embeddings and metastable clusters from time series data
Y Sun, Y Duan, H Gong, M Wang
Advances in Neural Information Processing Systems, 4561-4570, 2019
102019
Adaptive and robust multi-task learning
Y Duan, K Wang
arXiv preprint arXiv:2202.05250, 2022
92022
Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
Y Duan, M Wang, Z Wen, Y Yuan
SIAM Journal on Matrix Analysis and Applications 41 (1), 244-278, 2020
82020
Learning good state and action representations via tensor decomposition
C Ni, A Zhang, Y Duan, M Wang
2021 IEEE International Symposium on Information Theory (ISIT), 1682-1687, 2021
72021
Bootstrapping fitted Q-evaluation for off-policy inference
B Hao, X Ji, Y Duan, H Lu, C Szepesvari, M Wang
International Conference on Machine Learning, 4074-4084, 2021
72021
Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
Y Duan, MJ Wainwright
arXiv preprint arXiv:2211.03899, 2022
2022
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–13