Nan Jiang

Faculty of Information Technology, Beijing University of Technology, Beijing, China, Beijing Key Laboratory of Trusted Computing, Beijing, China, National Engineering Laboratory for Critical Technologies of Information Security Classified Protection, Beijing, China

A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation

May 24, 2020
Xiuyu Wu, Nan Jiang, Yunfang Wu


  Access Model/Code and Paper
Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison

Apr 09, 2020
Tengyang Xie, Nan Jiang


  Access Model/Code and Paper
$Q^\star$ Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison

Mar 11, 2020
Tengyang Xie, Nan Jiang


  Access Model/Code and Paper
Minimax Confidence Interval for Off-Policy Evaluation and Policy Optimization

Feb 26, 2020
Nan Jiang, Jiawei Huang


  Access Model/Code and Paper
RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

Feb 08, 2020
Nan Jiang, Sheng Jin, Zhiyao Duan, Changshui Zhang


  Access Model/Code and Paper
Scale Match for Tiny Person Detection

Dec 23, 2019
Xuehui Yu, Yuqi Gong, Nan Jiang, Qixiang Ye, Zhenjun Han

* accepted by WACV2020 

  Access Model/Code and Paper
Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning

Nov 15, 2019
Cameron Voloshin, Hoang M. Le, Nan Jiang, Yisong Yue

* Main paper is 8 pages. The appendix contains many pages of tables 

  Access Model/Code and Paper
Minimax Weight and Q-Function Learning for Off-Policy Evaluation

Nov 02, 2019
Masatoshi Uehara, Nan Jiang


  Access Model/Code and Paper
Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles

Oct 23, 2019
Aditya Modi, Nan Jiang, Ambuj Tewari, Satinder Singh


  Access Model/Code and Paper
From Importance Sampling to Doubly Robust Policy Gradient

Oct 20, 2019
Jiawei Huang, Nan Jiang

* 30 pages; 1 figure 

  Access Model/Code and Paper
On Value Functions and the Agent-Environment Boundary

May 30, 2019
Nan Jiang

* 16 pages 

  Access Model/Code and Paper
Provably Efficient Q-Learning with Low Switching Cost

May 30, 2019
Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang


  Access Model/Code and Paper
Information-Theoretic Considerations in Batch Reinforcement Learning

May 01, 2019
Jinglin Chen, Nan Jiang

* Published in ICML 2019 

  Access Model/Code and Paper
Provably efficient RL with Rich Observations via Latent State Decoding

Jan 25, 2019
Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford


  Access Model/Code and Paper
Model-Based Reinforcement Learning in Contextual Decision Processes

Nov 21, 2018
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford

* 30 

  Access Model/Code and Paper
On Oracle-Efficient PAC RL with Rich Observations

Oct 31, 2018
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire

* appearing at NIPS 18; full paper including appendix 

  Access Model/Code and Paper
Why Do Neural Response Generation Models Prefer Universal Replies?

Aug 28, 2018
Bowen Wu, Nan Jiang, Zhifeng Gao, Suke Li, Wenge Rong, Baoxun Wang


  Access Model/Code and Paper
Hierarchical Imitation and Reinforcement Learning

Jun 09, 2018
Hoang M. Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III

* Proceedings of the 35th International Conference on Machine Learning (ICML 2018) 

  Access Model/Code and Paper
Image Classification Based on Quantum KNN Algorithm

May 16, 2018
Yijie Dang, Nan Jiang, Hao Hu, Zhuoxiao Ji, Wenyin Zhang

* 19 pages, 9 Postscript figures 

  Access Model/Code and Paper
Optimizing Recurrent Neural Networks Architectures under Time Constraints

Feb 21, 2018
Junqi Jin, Ziang Yan, Kun Fu, Nan Jiang, Changshui Zhang

* Withdrawn due to incompleteness and some overlaps with existing literatures, I will resubmit adding further results 

  Access Model/Code and Paper
Neural Network Architecture Optimization through Submodularity and Supermodularity

Feb 21, 2018
Junqi Jin, Ziang Yan, Kun Fu, Nan Jiang, Changshui Zhang

* Withdrawn due to incompleteness and some overlaps with existing literatures, I will resubmit adding further results 

  Access Model/Code and Paper
Hand Segmentation for Hand-Object Interaction from Depth map

Jan 10, 2018
Byeongkeun Kang, Kar-Han Tan, Nan Jiang, Hung-Shuo Tai, Daniel Tretter, Truong Q. Nguyen


  Access Model/Code and Paper
Markov Decision Processes with Continuous Side Information

Nov 15, 2017
Aditya Modi, Nan Jiang, Satinder Singh, Ambuj Tewari


  Access Model/Code and Paper
Repeated Inverse Reinforcement Learning

Nov 04, 2017
Kareem Amin, Nan Jiang, Satinder Singh

* The first two authors contributed equally to this work. The paper appears in NIPS 2017 

  Access Model/Code and Paper
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable

Dec 01, 2016
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire

* 42 pages, 1 figure 

  Access Model/Code and Paper
Word Embedding based Correlation Model for Question/Answer Matching

Nov 26, 2016
Yikang Shen, Wenge Rong, Nan Jiang, Baolin Peng, Jie Tang, Zhang Xiong

* AAAI (2017) 3511--3517 
* 8 pages, 2 figures 

  Access Model/Code and Paper
Doubly Robust Off-policy Value Evaluation for Reinforcement Learning

May 26, 2016
Nan Jiang, Lihong Li

* 14 pages; 4 figures; ICML 2016 

  Access Model/Code and Paper