Følg
Jiafan He
Jiafan He
PhD student, Department of Computer Science, UCLA
Verifisert e-postadresse på ucla.edu - Startside
Tittel
Sitert av
Sitert av
År
Provably efficient reinforcement learning for discounted mdps with feature mapping
D Zhou, J He, Q Gu
International Conference on Machine Learning, 12793-12802, 2021
1492021
Logarithmic regret for reinforcement learning with linear function approximation
J He, D Zhou, Q Gu
International Conference on Machine Learning, 4171-4180, 2021
1072021
Nearly minimax optimal reinforcement learning for linear markov decision processes
J He, H Zhao, D Zhou, Q Gu
International Conference on Machine Learning, 12790-12822, 2023
602023
Nearly optimal algorithms for linear contextual bandits with adversarial corruptions
J He, D Zhou, T Zhang, Q Gu
Advances in neural information processing systems 35, 34614-34625, 2022
582022
Nearly minimax optimal reinforcement learning for discounted MDPs
J He, D Zhou, Q Gu
Advances in Neural Information Processing Systems 34, 2021
512021
A simple and provably efficient algorithm for asynchronous federated contextual linear bandits
J He, T Wang, Y Min, Q Gu
Advances in neural information processing systems 35, 4762-4775, 2022
372022
Achieving a fairer future by changing the past
J He, AD Procaccia, CA Psomas, D Zeng
IJCAI'19, 2019
352019
Learning stochastic shortest path with linear function approximation
Y Min, J He, T Wang, Q Gu
International Conference on Machine Learning, 15584-15629, 2022
332022
Variance-dependent regret bounds for linear bandits and reinforcement learning: Adaptivity and computational efficiency
H Zhao, J He, D Zhou, T Zhang, Q Gu
The Thirty Sixth Annual Conference on Learning Theory, 4977-5020, 2023
322023
Near-optimal policy optimization algorithms for learning adversarial linear mixture mdps
J He, D Zhou, Q Gu
International Conference on Artificial Intelligence and Statistics, 4259-4280, 2022
32*2022
Reinforcement learning from human feedback with active queries
K Ji, J He, Q Gu
arXiv preprint arXiv:2402.09401, 2024
192024
Uniform-pac bounds for reinforcement learning with linear function approximation
J He, D Zhou, Q Gu
Advances in Neural Information Processing Systems 34, 2021
192021
Provably efficient representation learning in low-rank markov decision processes
W Zhang, J He, D Zhou, A Zhang, Q Gu
arXiv preprint arXiv:2106.11935, 2021
192021
Locally differentially private reinforcement learning for linear mixture markov decision processes
C Liao, J He, Q Gu
Asian Conference on Machine Learning, 627-642, 2023
182023
A nearly optimal and low-switching algorithm for reinforcement learning with general function approximation
H Zhao, J He, Q Gu
arXiv preprint arXiv:2311.15238, 2023
122023
Bandit learning with general function classes: Heteroscedastic noise and variance-dependent regret bounds
H Zhao, D Zhou, J He, Q Gu
122022
Cooperative multi-agent reinforcement learning: asynchronous communication and linear function approximation
Y Min, J He, T Wang, Q Gu
International Conference on Machine Learning, 24785-24811, 2023
112023
Pessimistic nonlinear least-squares value iteration for offline reinforcement learning
Q Di, H Zhao, J He, Q Gu
arXiv preprint arXiv:2310.01380, 2023
92023
On the interplay between misspecification and sub-optimality gap in linear contextual bandits
W Zhang, J He, Z Fan, Q Gu
International Conference on Machine Learning, 41111-41132, 2023
92023
On the sample complexity of learning infinite-horizon discounted linear kernel mdps
Y Chen, J He, Q Gu
International Conference on Machine Learning, 3149-3183, 2022
72022
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20