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 Mengdi Wang

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method


Feb 17, 2021
Junyu Zhang, Chengzhuo Ni, Zheng Yu, Csaba Szepesvari, Mengdi Wang


  Access Paper or Ask Questions

Bootstrapping Statistical Inference for Off-Policy Evaluation


Feb 09, 2021
Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang


  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

High-Dimensional Sparse Linear Bandits


Nov 08, 2020
Botao Hao, Tor Lattimore, Mengdi Wang

* Accepted by NeurIPS 2020 

  Access Paper or Ask Questions

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient


Nov 08, 2020
Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári, Mengdi Wang


  Access Paper or Ask Questions

Online Sparse Reinforcement Learning


Nov 08, 2020
Botao Hao, Tor Lattimore, Csaba Szepesvári, Mengdi Wang


  Access Paper or Ask Questions

Generalized Leverage Score Sampling for Neural Networks


Sep 21, 2020
Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu


  Access Paper or Ask Questions

Variational Policy Gradient Method for Reinforcement Learning with General Utilities


Jul 04, 2020
Junyu Zhang, Alec Koppel, Amrit Singh Bedi, Csaba Szepesvari, Mengdi Wang


  Access Paper or Ask Questions

Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python


Jun 27, 2020
Jason Ge, Xingguo Li, Haoming Jiang, Han Liu, Tong Zhang, Mengdi Wang, Tuo Zhao

* Journal of Machine Learning Research 20 (2019): 44-1 

  Access Paper or Ask Questions

Model-Based Reinforcement Learning with Value-Targeted Regression


Jun 01, 2020
Alex Ayoub, Zeyu Jia, Csaba Szepesvari, Mengdi Wang, Lin F. Yang


  Access Paper or Ask Questions

Cautious Reinforcement Learning via Distributional Risk in the Dual Domain


Feb 27, 2020
Junyu Zhang, Amrit Singh Bedi, Mengdi Wang, Alec Koppel


  Access Paper or Ask Questions

Sketching Transformed Matrices with Applications to Natural Language Processing


Feb 23, 2020
Yingyu Liang, Zhao Song, Mengdi Wang, Lin F. Yang, Xin Yang

* AISTATS 2020 

  Access Paper or Ask Questions

Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation


Feb 21, 2020
Yaqi Duan, Mengdi Wang


  Access Paper or Ask Questions

Unsupervised Common Question Generation from Multiple Documents using Reinforced Contrastive Coordinator


Nov 08, 2019
Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan


  Access Paper or Ask Questions

Continuous Control with Contexts, Provably


Oct 30, 2019
Simon S. Du, Ruosong Wang, Mengdi Wang, Lin F. Yang


  Access Paper or Ask Questions

Characterizing Deep Learning Training Workloads on Alibaba-PAI


Oct 14, 2019
Mengdi Wang, Chen Meng, Guoping Long, Chuan Wu, Jun Yang, Wei Lin, Yangqing Jia

* Accepted by IISWC2019 

  Access Paper or Ask Questions

Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity


Aug 29, 2019
Aaron Sidford, Mengdi Wang, Lin F. Yang, Yinyu Ye


  Access Paper or Ask Questions

Voting-Based Multi-Agent Reinforcement Learning


Jul 02, 2019
Yue Xu, Zengde Deng, Mengdi Wang, Wenjun Xu, Anthony Man-Cho So, Shuguang Cui


  Access Paper or Ask Questions

Learning Markov models via low-rank optimization


Jun 28, 2019
Ziwei Zhu, Xudong Li, Mengdi Wang, Anru Zhang

* 40 pages, 4 figures. arXiv admin note: text overlap with arXiv:1804.00795 

  Access Paper or Ask Questions

Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound


Jun 13, 2019
Lin F. Yang, Mengdi Wang


  Access Paper or Ask Questions

Feature-Based Q-Learning for Two-Player Stochastic Games


Jun 02, 2019
Zeyu Jia, Lin F. Yang, Mengdi Wang

* 23 pages 

  Access Paper or Ask Questions

Learning low-dimensional state embeddings and metastable clusters from time series data


Jun 01, 2019
Yifan Sun, Yaqi Duan, Hao Gong, Mengdi Wang


  Access Paper or Ask Questions

RL4health: Crowdsourcing Reinforcement Learning for Knee Replacement Pathway Optimization


May 24, 2019
Hao Lu, Mengdi Wang


  Access Paper or Ask Questions

Reinforcement Leaning in Feature Space: Matrix Bandit, Kernels, and Regret Bound


May 24, 2019
Lin F. Yang, Mengdi Wang


  Access Paper or Ask Questions

Learning to Control in Metric Space with Optimal Regret


May 05, 2019
Lin F. Yang, Chengzhuo Ni, Mengdi Wang


  Access Paper or Ask Questions

Sample-Optimal Parametric Q-Learning with Linear Transition Models


Feb 13, 2019
Lin F. Yang, Mengdi Wang


  Access Paper or Ask Questions

Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks


Nov 21, 2018
Mengdi Wang, Qing Zhang, Jun Yang, Xiaoyuan Cui, Wei Lin

* 7 pages, 7 figures 

  Access Paper or Ask Questions

State Aggregation Learning from Markov Transition Data


Nov 06, 2018
Yaqi Duan, Zheng Tracy Ke, Mengdi Wang


  Access Paper or Ask Questions

A bird's-eye view on coherence, and a worm's-eye view on cohesion


Nov 01, 2018
Woon Sang Cho, Pengchuan Zhang, Yizhe Zhang, Xiujun Li, Michel Galley, Mengdi Wang, Jianfeng Gao


  Access Paper or Ask Questions

Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains


Oct 14, 2018
Yaqi Duan, Mengdi Wang, Zaiwen Wen, Yaxiang Yuan


  Access Paper or Ask Questions