Följ
Ming Yin
Titel
Citeras av
Citeras av
År
Near-optimal provable uniform convergence in offline policy evaluation for reinforcement learning
M Yin, Y Bai, YX Wang
(AISTATS) International Conference on Artificial Intelligence and Statistics …, 2021
50*2021
Asymptotically efficient off-policy evaluation for tabular reinforcement learning
M Yin, YX Wang
(AISTATS) International Conference on Artificial Intelligence and Statistics …, 2020
472020
Near-optimal offline reinforcement learning via double variance reduction
M Yin, Y Bai, YX Wang
(NeurIPS) Advances in neural information processing systems 34, 7677-7688, 2021
402021
Towards instance-optimal offline reinforcement learning with pessimism
M Yin, YX Wang
(NeurIPS) Advances in neural information processing systems 34, 4065-4078, 2021
252021
Near-optimal offline reinforcement learning with linear representation: Leveraging variance information with pessimism
M Yin, Y Duan, M Wang, YX Wang
(ICLR) Internation Conference on Learning Representations, 2022
172022
Optimal uniform ope and model-based offline reinforcement learning in time-homogeneous, reward-free and task-agnostic settings
M Yin, YX Wang
(NeurIPS) Advances in Neural Information Processing Systems, 2021, 2021
72021
Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
M Yin, W Chen, M Wang, YX Wang
(UAI) The 38th Conference on Uncertainty in Artificial Intelligence, 2022
22022
Sample-Efficient Reinforcement Learning with Switching Cost
D Qiao, M Yin, M Min, YX Wang
(ICML) International Conference on Machine Learning, 2022, 2022
12022
On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
T Nguyen-Tang, M Yin, S Gupta, S Venkatesh, R Arora
(AAAI) Association for the Advancement of Artificial Intelligence, 2023, 2023
2023
Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
M Yin, M Wang, YX Wang
arXiv preprint arXiv:2210.00750, 2022
2022
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
K Zhang, M Yin, YX Wang
arXiv preprint arXiv:2206.05916, 2022
2022
Offline Reinforcement Learning with Closed-form Policy Improvement Operators
J Li, E Zhang, M Yin, B Qinxun, YX Wang, WY Wang
(NeurIPS workshop) Offline Reinforcement Learning Workshop 2022, 2022
2022
Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality (Supplementary material)
M Yin, W Chen, M Wang, YX Wang
(UAI) Supplementary material, 2022
2022
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–13