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 Yihao Feng

Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning

Jan 01, 2022
Ziyang Tang, Yihao Feng, Qiang Liu

  Access Paper or Ask Questions

Unsupervised Out-of-Domain Detection via Pre-trained Transformers

Jun 02, 2021
Keyang Xu, Tongzheng Ren, Shikun Zhang, Yihao Feng, Caiming Xiong

* Accepted by ACL 2021. Code is available at 

  Access Paper or Ask Questions

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Apr 24, 2021
Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu

* 10 pages, accepted to NAACL 2021 

  Access Paper or Ask Questions

Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds

Mar 09, 2021
Yihao Feng, Ziyang Tang, Na Zhang, Qiang Liu

* 33 Pages, 5 figures, extended version of a paper with the same title accepted by ICLR2021 

  Access Paper or Ask Questions

Transparent Interpretation with Knockouts

Nov 01, 2020
Xing Han, Yihao Feng, Na Zhang, Qiang Liu

  Access Paper or Ask Questions

Off-Policy Interval Estimation with Lipschitz Value Iteration

Oct 29, 2020
Ziyang Tang, Yihao Feng, Na Zhang, Jian Peng, Qiang Liu

* To appear at NeurIPS 2020 

  Access Paper or Ask Questions

Accountable Off-Policy Evaluation With Kernel Bellman Statistics

Aug 15, 2020
Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

* 22 pages, 4 figures, ICML 2020 

  Access Paper or Ask Questions

Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation

Oct 16, 2019
Ziyang Tang, Yihao Feng, Lihong Li, Dengyong Zhou, Qiang Liu

  Access Paper or Ask Questions

A Kernel Loss for Solving the Bellman Equation

May 25, 2019
Yihao Feng, Lihong Li, Qiang Liu

  Access Paper or Ask Questions

Knowledge-guided Semantic Computing Network

Sep 29, 2018
Guangming Shi, Zhongqiang Zhang, Dahua Gao, Xuemei Xie, Yihao Feng, Xinrui Ma, Danhua Liu

* 13 pages, 13 figures 

  Access Paper or Ask Questions

Action-depedent Control Variates for Policy Optimization via Stein's Identity

Feb 23, 2018
Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu

* The first two authors contributed equally. Author ordering determined by coin flip over a Google Hangout. Accepted by ICLR 2018 

  Access Paper or Ask Questions

Two Methods For Wild Variational Inference

Oct 30, 2017
Qiang Liu, Yihao Feng

  Access Paper or Ask Questions

Learning to Draw Samples with Amortized Stein Variational Gradient Descent

Oct 30, 2017
Yihao Feng, Dilin Wang, Qiang Liu

* Accepted by UAI 2017 

  Access Paper or Ask Questions