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 Tengyu Xu

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

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

Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry


Feb 17, 2021
Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang

* To appear in ICLR 2021 

  Access Paper or Ask Questions

A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis


Nov 17, 2020
Tengyu Xu, Yingbin Liang, Guanghui Lan

* Submitted for conference publication 

  Access Paper or Ask Questions

Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms


Nov 10, 2020
Tengyu Xu, Yingbin Liang

* Submitted for conference publication 

  Access Paper or Ask Questions

When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence


Jun 25, 2020
Ziwei Guan, Tengyu Xu, Yingbin Liang

* Submitted for publication 

  Access Paper or Ask Questions

Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization


Jun 17, 2020
Tengyu Xu, Zhe Wang, Yingbin Liang, H. Vincent Poor

* 43 pages, 6 figures 

  Access Paper or Ask Questions

Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms


May 08, 2020
Tengyu Xu, Zhe Wang, Yingbin Liang

* The results of this paper were initially submitted for publication in February 2020 

  Access Paper or Ask Questions

Improving Sample Complexity Bounds for Actor-Critic Algorithms


Apr 28, 2020
Tengyu Xu, Zhe Wang, Yingbin Liang

* 30 pages, 0 figure 

  Access Paper or Ask Questions

Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling


Feb 15, 2020
Huaqing Xiong, Tengyu Xu, Yingbin Liang, Wei Zhang


  Access Paper or Ask Questions

Reanalysis of Variance Reduced Temporal Difference Learning


Jan 10, 2020
Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang

* To appear in ICLR 2020 

  Access Paper or Ask Questions

Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples


Sep 26, 2019
Tengyu Xu, Shaofeng Zou, Yingbin Liang

* To appear in NeurIPS 2019 

  Access Paper or Ask Questions

Finite-Sample Analysis for SARSA and Q-Learning with Linear Function Approximation


Feb 06, 2019
Shaofeng Zou, Tengyu Xu, Yingbin Liang


  Access Paper or Ask Questions

When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models?


Oct 15, 2018
Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang


  Access Paper or Ask Questions