Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zhaoran Wang

A Unified Off-Policy Evaluation Approach for General Value Function


Jul 06, 2021
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang

* submitted for publication 

  Access Paper or Ask Questions

Gap-Dependent Bounds for Two-Player Markov Games


Jul 01, 2021
Zehao Dou, Zhuoran Yang, Zhaoran Wang, Simon S. Du

* 34 pages 

  Access Paper or Ask Questions

Randomized Exploration for Reinforcement Learning with General Value Function Approximation


Jun 15, 2021
Haque Ishfaq, Qiwen Cui, Viet Nguyen, Alex Ayoub, Zhuoran Yang, Zhaoran Wang, Doina Precup, Lin F. Yang

* 32 page, 5 figures, in Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021 

  Access Paper or Ask Questions

Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach


May 18, 2021
Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha


  Access Paper or Ask Questions

Principled Exploration via Optimistic Bootstrapping and Backward Induction


May 17, 2021
Chenjia Bai, Lingxiao Wang, Lei Han, Jianye Hao, Animesh Garg, Peng Liu, Zhaoran Wang

* ICML 2021 

  Access Paper or Ask Questions

Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality


Feb 27, 2021
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang

* Submitted for publication 

  Access Paper or Ask Questions

Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning


Feb 19, 2021
Luofeng Liao, Zuyue Fu, Zhuoran Yang, Mladen Kolar, Zhaoran Wang

* under review 

  Access Paper or Ask Questions

A Momentum-Assisted Single-Timescale Stochastic Approximation Algorithm for Bilevel Optimization


Feb 15, 2021
Prashant Khanduri, Siliang Zeng, Mingyi Hong, Hoi-To Wai, Zhaoran Wang, Zhuoran Yang

* 34 Pages, 10 Figures 

  Access Paper or Ask Questions

Provably Training Neural Network Classifiers under Fairness Constraints


Dec 30, 2020
You-Lin Chen, Zhaoran Wang, Mladen Kolar


  Access Paper or Ask Questions

Is Pessimism Provably Efficient for Offline RL?


Dec 30, 2020
Ying Jin, Zhuoran Yang, Zhaoran Wang

* 53 pages, 3 figures 

  Access Paper or Ask Questions

Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy


Dec 28, 2020
Han Zhong, Ethan X. Fang, Zhuoran Yang, Zhaoran Wang

* 45 pages 

  Access Paper or Ask Questions

Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization


Dec 21, 2020
Zhuoran Yang, Yufeng Zhang, Yongxin Chen, Zhaoran Wang

* 58 pages 

  Access Paper or Ask Questions

Bridging Exploration and General Function Approximation in Reinforcement Learning: Provably Efficient Kernel and Neural Value Iterations


Nov 09, 2020
Zhuoran Yang, Chi Jin, Zhaoran Wang, Mengdi Wang, Michael I. Jordan

* 76 pages. The short version of this work appears in NeurIPS 2020 

  Access Paper or Ask Questions

End-to-End Learning and Intervention in Games


Oct 26, 2020
Jiayang Li, Jing Yu, Yu Marco Nie, Zhaoran Wang

* To be published in Advances in Neural Information Processing Systems 33 (NeurIPS 2020) 

  Access Paper or Ask Questions

Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning


Oct 17, 2020
Chenjia Bai, Peng Liu, Zhaoran Wang, Kaiyu Liu, Lingxiao Wang, Yingnan Zhao

* associated videos at https://sites.google.com/view/exploration-vdm 

  Access Paper or Ask Questions

Provable Fictitious Play for General Mean-Field Games


Oct 08, 2020
Qiaomin Xie, Zhuoran Yang, Zhaoran Wang, Andreea Minca


  Access Paper or Ask Questions

Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection


Sep 04, 2020
Yining Wang, Yi Chen, Ethan X. Fang, Zhaoran Wang, Runze Li

* 54 pages, 4 figures 

  Access Paper or Ask Questions

Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning


Aug 23, 2020
Shuang Qiu, Zhuoran Yang, Xiaohan Wei, Jieping Ye, Zhaoran Wang

* 45 pages; initial draft submitted in Feb, 2020 

  Access Paper or Ask Questions

Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time


Aug 16, 2020
Weichen Wang, Jiequn Han, Zhuoran Yang, Zhaoran Wang

* 28 pages, 3 figures 

  Access Paper or Ask Questions

Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy


Aug 02, 2020
Zuyue Fu, Zhuoran Yang, Zhaoran Wang


  Access Paper or Ask Questions

A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic


Jul 10, 2020
Mingyi Hong, Hoi-To Wai, Zhaoran Wang, Zhuoran Yang


  Access Paper or Ask Questions

Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion


Jul 04, 2020
Yi Chen, Jinglin Chen, Jing Dong, Jian Peng, Zhaoran Wang


  Access Paper or Ask Questions

Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach


Jul 02, 2020
Luofeng Liao, You-Lin Chen, Zhuoran Yang, Bo Dai, Zhaoran Wang, Mladen Kolar

* Submitted to NeurIPS 2020. Under review 

  Access Paper or Ask Questions

Dynamic Regret of Policy Optimization in Non-stationary Environments


Jun 30, 2020
Yingjie Fei, Zhuoran Yang, Zhaoran Wang, Qiaomin Xie


  Access Paper or Ask Questions

On the Global Optimality of Model-Agnostic Meta-Learning


Jun 23, 2020
Lingxiao Wang, Qi Cai, Zhuoran Yang, Zhaoran Wang

* 41 pages; accepted to ICML; initial draft submitted in Feb, 2020 

  Access Paper or Ask Questions

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret


Jun 22, 2020
Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang, Qiaomin Xie


  Access Paper or Ask Questions

Provably Efficient Causal Reinforcement Learning with Confounded Observational Data


Jun 22, 2020
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang

* 42 pages, 4 figures 

  Access Paper or Ask Questions

Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning


Jun 21, 2020
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang

* 31 pages; accepted to ICML; initial draft submitted in Feb, 2020 

  Access Paper or Ask Questions