Tengyu Xu

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 34

Top Topics

Reinforcement Learning Algorithms

Asymptotic Convergence

Reinforcement Learning

Convex Minimization

Top Venues

Publications

Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan
Faster algorithm and sharper analysis for constrained Markov decision process. Oper. Res. Lett. 54 (2024)
Xiumin Shang, Tengyu Xu, Ioannis Karamouzas, Marcelo Kallmann
Constraint-based multi-agent reinforcement learning for collaborative tasks. Comput. Animat. Virtual Worlds 34 (3-4) (2023)
Huaqing Xiong, Tengyu Xu, Lin Zhao, Yingbin Liang, Wei Zhang
Deterministic policy gradient: Convergence analysis. UAI (2022)
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang
A Unifying Framework of Off-Policy General Value Function Evaluation. NeurIPS (2022)
Sen Lin, Jialin Wan, Tengyu Xu, Yingbin Liang, Junshan Zhang
Model-Based Offline Meta-Reinforcement Learning with Regularization. ICLR (2022)
Sen Lin, Jialin Wan, Tengyu Xu, Yingbin Liang, Junshan Zhang
Model-Based Offline Meta-Reinforcement Learning with Regularization. CoRR (2022)
Ziwei Guan, Tengyu Xu, Yingbin Liang
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method. ICLR (2022)
Tengyu Xu, Yingbin Liang
Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward. CoRR (2022)
Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang
Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry. CoRR (2021)
Ziwei Guan, Tengyu Xu, Yingbin Liang
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method. CoRR (2021)
Tengyu Xu, Yingbin Liang, Guanghui Lan
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee. ICML (2021)
Ziwei Guan, Tengyu Xu, Yingbin Liang
When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence. AISTATS (2021)
Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang
Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry. ICLR (2021)
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang
A Unified Off-Policy Evaluation Approach for General Value Function. CoRR (2021)
Huaqing Xiong, Tengyu Xu, Yingbin Liang, Wei Zhang
Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling. AAAI (2021)
Tianjiao Li, Ziwei Guan, Shaofeng Zou, Tengyu Xu, Yingbin Liang, Guanghui Lan
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process. CoRR (2021)
Tengyu Xu, Yingbin Liang
Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms. AISTATS (2021)
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality. CoRR (2021)
Tengyu Xu, Zhuoran Yang, Zhaoran Wang, Yingbin Liang
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality. ICML (2021)
Tengyu Xu, Zhe Wang, Yingbin Liang
Improving Sample Complexity Bounds for Actor-Critic Algorithms. CoRR (2020)
Tengyu Xu, Zhe Wang, Yingbin Liang, H. Vincent Poor
Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization. CoRR (2020)
Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang
Reanalysis of Variance Reduced Temporal Difference Learning. ICLR (2020)
Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang
Reanalysis of Variance Reduced Temporal Difference Learning. CoRR (2020)
Tengyu Xu, Zhe Wang, Yingbin Liang
Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms. NeurIPS (2020)
Tengyu Xu, Zhe Wang, Yingbin Liang
Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms. CoRR (2020)
Ziwei Guan, Tengyu Xu, Yingbin Liang
When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence. CoRR (2020)
Tengyu Xu, Yingbin Liang, Guanghui Lan
A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis. CoRR (2020)
Tengyu Xu, Yingbin Liang
Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms. CoRR (2020)
Huaqing Xiong, Tengyu Xu, Yingbin Liang, Wei Zhang
Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling. CoRR (2020)
Tengyu Xu, Shaofeng Zou, Yingbin Liang
Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples. NeurIPS (2019)
Shaofeng Zou, Tengyu Xu, Yingbin Liang
Finite-Sample Analysis for SARSA and Q-Learning with Linear Function Approximation. CoRR (2019)
Tengyu Xu, Shaofeng Zou, Yingbin Liang
Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples. CoRR (2019)
Shaofeng Zou, Tengyu Xu, Yingbin Liang
Finite-Sample Analysis for SARSA with Linear Function Approximation. NeurIPS (2019)
Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang
Convergence of SGD in Learning ReLU Models with Separable Data. CoRR (2018)