Follow
Zeyu Jia
Zeyu Jia
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Model-based reinforcement learning with value-targeted regression
A Ayoub, Z Jia, C Szepesvari, M Wang, L Yang
International Conference on Machine Learning, 463-474, 2020
3022020
Minimax-optimal off-policy evaluation with linear function approximation
Y Duan, Z Jia, M Wang
International Conference on Machine Learning, 2701-2709, 2020
1542020
Model-based reinforcement learning with value-targeted regression
Z Jia, L Yang, C Szepesvari, M Wang
Learning for Dynamics and Control, 666-686, 2020
662020
Feature-based q-learning for two-player stochastic games
Z Jia, LF Yang, M Wang
arXiv preprint arXiv:1906.00423, 2019
562019
Intrinsic dimension estimation using Wasserstein distances
A Block, Z Jia, Y Polyanskiy, A Rakhlin
arXiv preprint arXiv:2106.04018, 2021
112021
Rate of convergence of the smoothed empirical Wasserstein distance
A Block, Z Jia, Y Polyanskiy, A Rakhlin
arXiv preprint arXiv:2205.02128, 2022
52022
Entropic characterization of optimal rates for learning Gaussian mixtures
Z Jia, Y Polyanskiy, Y Wu
The Thirty Sixth Annual Conference on Learning Theory, 4296-4335, 2023
22023
Search direction correction with normalized gradient makes first-order methods faster
Y Wang, Z Jia, Z Wen
SIAM Journal on Scientific Computing 43 (5), A3184-A3211, 2021
22021
Towards solving 2-TBSG efficiently
Z Jia, Z Wen, Y Ye
Optimization Methods and Software 35 (4), 706-721, 2020
22020
When is Agnostic Reinforcement Learning Statistically Tractable?
Z Jia, G Li, A Rakhlin, A Sekhari, N Srebro
Advances in Neural Information Processing Systems 36, 2024
12024
Linear reinforcement learning with ball structure action space
Z Jia, R Jia, D Madeka, DP Foster
International Conference on Algorithmic Learning Theory, 755-775, 2023
12023
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
Z Jia, A Rakhlin, A Sekhari, CY Wei
arXiv preprint arXiv:2403.17091, 2024
2024
Non-parametric threshold for smoothed empirical Wasserstein distance
Z Jia
Massachusetts Institute of Technology, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–13