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 Hengshuai Yao

Breaking the Deadly Triad with a Target Network


Feb 09, 2021
Shangtong Zhang, Hengshuai Yao, Shimon Whiteson


  Access Paper or Ask Questions

Variance-Reduced Off-Policy Memory-Efficient Policy Search


Sep 14, 2020
Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh, Hengshuai Yao, Tianbao Yang, Bo Liu


  Access Paper or Ask Questions

Beyond Prioritized Replay: Sampling States in Model-Based RL via Simulated Priorities


Jul 19, 2020
Jincheng Mei, Yangchen Pan, Martha White, Amir-massoud Farahmand, Hengshuai Yao

* The paper is under review 

  Access Paper or Ask Questions

Towards a practical measure of interference for reinforcement learning


Jul 07, 2020
Vincent Liu, Adam White, Hengshuai Yao, Martha White

* 18 pages 

  Access Paper or Ask Questions

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Inputs


Feb 07, 2020
Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand

* The first three authors listed contributed equally 

  Access Paper or Ask Questions

One-Shot Weakly Supervised Video Object Segmentation


Dec 18, 2019
Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand


  Access Paper or Ask Questions

Provably Convergent Off-Policy Actor-Critic with Function Approximation


Nov 11, 2019
Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

* Optimization Foundations of Reinforcement Learning Workshop at NeurIPS 2019 

  Access Paper or Ask Questions

Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans


Nov 08, 2019
Jun Jin, Nhat M. Nguyen, Nazmus Sakib, Daniel Graves, Hengshuai Yao, Martin Jagersand


  Access Paper or Ask Questions

Is Fast Adaptation All You Need?


Oct 03, 2019
Khurram Javed, Hengshuai Yao, Martha White

* Meta Learning Workshop, NeurIPS 2019, 2 figures, MRCL, MAML 

  Access Paper or Ask Questions

Hill Climbing on Value Estimates for Search-control in Dyna


Jul 04, 2019
Yangchen Pan, Hengshuai Yao, Amir-massoud Farahmand, Martha White

* IJCAI 2019 

  Access Paper or Ask Questions

Distributional Reinforcement Learning for Efficient Exploration


May 13, 2019
Borislav Mavrin, Shangtong Zhang, Hengshuai Yao, Linglong Kong, Kaiwen Wu, Yaoliang Yu

* ICML, 2019 

  Access Paper or Ask Questions

Reinforcing Classical Planning for Adversary Driving Scenarios


Mar 20, 2019
Nazmus Sakib, Hengshuai Yao, Hong Zhang


  Access Paper or Ask Questions

Deep Reinforcement Learning with Decorrelation


Mar 18, 2019
Borislav Mavrin, Hengshuai Yao, Linglong Kong


  Access Paper or Ask Questions

QUOTA: The Quantile Option Architecture for Reinforcement Learning


Nov 07, 2018
Shangtong Zhang, Borislav Mavrin, Linglong Kong, Bo Liu, Hengshuai Yao

* AAAI 2019 

  Access Paper or Ask Questions

ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search


Nov 06, 2018
Shangtong Zhang, Hao Chen, Hengshuai Yao

* AAAI 2019 

  Access Paper or Ask Questions

Negative Log Likelihood Ratio Loss for Deep Neural Network Classification


Apr 27, 2018
Donglai Zhu, Hengshuai Yao, Bei Jiang, Peng Yu


  Access Paper or Ask Questions

Practical Issues of Action-conditioned Next Image Prediction


Feb 08, 2018
Donglai Zhu, Hao Chen, Hengshuai Yao, Masoud Nosrati, Peyman Yadmellat, Yunfei Zhang

* 12 pages; 7 figures 

  Access Paper or Ask Questions