OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
hengshuai yao
Researcher, Game AI, Sony AI
Researcher, Computing Science, University of Alberta
Joined
October 2017
Names
hengshuai yao
(Preferred)
,
Hengshuai Yao
Emails
****@gmail.com
(Confirmed)
,
****@huawei.com
(Confirmed)
,
****@ualberta.ca
(Confirmed)
,
****@sony.com
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Career & Education History
Researcher
Game AI,
Sony AI
(sony.com)
2022
–
Present
Researcher
Computing Science,
University of Alberta
(ualberta.ca)
2020
–
Present
Principal Researcher
HiSilicon,
Huawei Technologies Ltd.
(huawei.com)
2017
–
2022
PhD student
Computing Science,
University of Alberta
(ualberta.ca)
2008
–
2014
M.E student
Computer Science and engineering,
Tsinghua University
(tsinghua.edu.cn)
2003
–
2006
Advisors, Relations & Conflicts
PhD Advisor
csaba szepesvari
2008
–
2014
PhD Advisor
rich sutton
2008
–
2014
Expertise
SGD
Present
deep learning
2020
–
Present
reinforcement learning
2008
–
Present
Publications
Value Shaping: Bias Reduction in Bellman Error for Deep Reinforcement Learning
Xing Chen
,
Xiaofeng Cao
,
Hechang Chen
,
hengshuai yao
,
Bo An
,
Yi Chang
ICLR 2026 Conference Withdrawn Submission
Readers:
Everyone
Careful at Estimation and Bold at Exploration for Deterministic Policy Gradient Algorithm
Xing Chen
,
Yijun Liu
,
Shutong Zhang
,
Siyuan Guo
,
Zhaogeng Liu
,
Yu Jin
,
haiyin piao
,
Hechang Chen
,
Hengshuai Yao
,
Yi Chang
Submitted to ICLR 2024
Readers:
Everyone
The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure
Xing Chen
,
Dongcui Diao
,
Hechang Chen
,
Hengshuai Yao
,
haiyin piao
,
Zhixiao Sun
,
Zhiwei Yang
,
Randy Goebel
,
Bei Jiang
,
Yi Chang
10 May 2023
OpenReview Archive Direct Upload
Readers:
Everyone
Class Interference of Deep Networks
Dongcui Diao
,
Hengshuai Yao
,
Bei Jiang
Published: 01 Feb 2023, Last Modified: 13 Feb 2023
Submitted to ICLR 2023
Readers:
Everyone
Understanding and Mitigating the Limitations of Prioritized Experience Replay
Yangchen Pan
,
Jincheng Mei
,
Amir-massoud Farahmand
,
Martha White
,
Hengshuai Yao
,
Mohsen Rohani
,
Jun Luo
Published: 20 May 2022, Last Modified: 05 May 2023
UAI 2022 Poster
Readers:
Everyone
Sigmoidally Preconditioned Off-policy Learning: a new exploration method for reinforcement learning
Xing Chen
,
Dongcui Diao
,
Hechang Chen
,
Hengshuai Yao
,
Jielong Yang
,
Haiyin Piao
,
Zhixiao Sun
,
Bei Jiang
,
Yi Chang
2022 (modified: 15 Nov 2022)
CoRR 2022
Readers:
Everyone
Class Interference of Deep Neural Networks
Dongcui Diao
,
Hengshuai Yao
,
Bei Jiang
2022 (modified: 15 Nov 2022)
CoRR 2022
Readers:
Everyone
Understanding and mitigating the limitations of prioritized experience replay
Yangchen Pan
,
Jincheng Mei
,
Amir-massoud Farahmand
,
Martha White
,
Hengshuai Yao
,
Mohsen Rohani
,
Jun Luo
2022 (modified: 15 Nov 2022)
UAI 2022
Readers:
Everyone
Learning to Accelerate by the Methods of Step-size Planning
Hengshuai Yao
2022 (modified: 15 Nov 2022)
CoRR 2022
Readers:
Everyone
Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities
Yangchen Pan
,
Jincheng Mei
,
Amir-massoud Farahmand
,
Martha White
,
Hengshuai Yao
,
Mohsen Rohani
,
Jun Luo
Published: 28 Jan 2022, Last Modified: 12 Oct 2025
ICLR 2022 Submitted
Readers:
Everyone
View all 59 publications
Co-Authors
Adam M White
Adam White
Amir-massoud Farahmand
Bei Jiang
Bernardo Ávila Pires
Bo An
Bo Liu
Boris N. Oreshkin
Borislav Mavrin
Chi-Hoon Lee
Csaba Szepesvári
Dale Schuurmans
Daniel Graves
Daoming Lyu
Di Niu
Diao Dongcui
Dongcui Diao
Donglai Zhu
Farzin Maghoul
Fred X. Han
Guangjian Tian
Guodong Li
Haiyin Piao
Hao Chen
Hechang Chen
View all 95 co-authors