Dongruo Zhou

发表

Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs

Quanquan Gu, Jiafan He, Dongruo Zhou, 2021, AISTATS.

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

Quanquan Gu, Jiafan He, Dongruo Zhou, 2020, NeurIPS.

Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games

Quanquan Gu, Dongruo Zhou, Zixiang Chen, 2021, ALT.

Linear Contextual Bandits with Adversarial Corruptions pdf

Quanquan Gu, Dongruo Zhou, Heyang Zhao, 2021, ArXiv.

Iterative Teacher-Aware Learning pdf

Song-Chun Zhu, Ying Nian Wu, Quanquan Gu, 2021, NeurIPS.

Almost Optimal Algorithms for Two-player Zero-Sum Markov Games with Linear Function Approximation

Quanquan Gu, Dongruo Zhou, Zixiang Chen, 2021 .

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Quanquan Gu, Jiafan He, Dongruo Zhou, 2022, ArXiv.

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Quanquan Gu, Jiafan He, Dongruo Zhou, 2022, NeurIPS.

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium

Michael I. Jordan, Quanquan Gu, C. J. Li, 2022, ArXiv.

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Quanquan Gu, Dongruo Zhou, 2022, NeurIPS.

Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

Quanquan Gu, Dongruo Zhou, Zixiang Chen, 2021, ALT.

Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

Quanquan Gu, Jiafan He, Dongruo Zhou, 2022, ICML.

Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency

Quanquan Gu, Jiafan He, Dongruo Zhou, 2023, COLT.

Pure Exploration in Kernel and Neural Bandits

Quanquan Gu, R. Nowak, R. Willett, 2021, NeurIPS.

Variance-Aware Off-Policy Evaluation with Linear Function Approximation pdf

Quanquan Gu, Tianhao Wang, Yifei Min, 2021, NeurIPS.

Learning Two-Player Markov Games: Neural Function Approximation and Correlated Equilibrium

M.I. Jordan, Quanquan Gu, C. J. Li, 2022, Neural Information Processing Systems.

Learning Neural Contextual Bandits through Perturbed Rewards

Quanquan Gu, Dongruo Zhou, Weitong Zhang, 2022, ICLR.

Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation pdf

Quanquan Gu, Dongruo Zhou, Weitong Zhang, 2021, NeurIPS.

Provably Efficient Representation Learning in Low-rank Markov Decision Processes pdf

Quanquan Gu, Amy Zhang, Jiafan He, 2021, ArXiv.

Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation pdf

Quanquan Gu, Jiafan He, Dongruo Zhou, 2021, NeurIPS.

Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits

Quanquan Gu, Jiafan He, Dongruo Zhou, 2022, ICML.

Provably efficient representation selection in Low-rank Markov Decision Processes: from online to offline RL

Quanquan Gu, Amy Zhang, Jiafan He, 2023, UAI.

Gradient descent optimizes over-parameterized deep ReLU networks

Quanquan Gu, Difan Zou, Yuanbin Cao, 2019, Machine Learning.

Provably efficient representation selection in Low-rank Markov Decision Processes: from online to offline RL

Quanquan Gu, Amy Zhang, Jiafan He, 2021, UAI.

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path

Quanquan Gu, Jiafan He, Dongruo Zhou, 2024, ICML.