Yuhui Wang

Yuhui Wang

Auto-generated profile, based on publicly available information

Yuhui Wang

King Abdullah University of Science and Technology

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 June 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XYXinghu Yao
Xinghu Yao
CWChao Wen
Chao Wen
YWYuhui Wang
Yuhui Wang
XTXiaoyang Tan
Xiaoyang Tan
Learning a stable and generalizable centralized value function (CVF) is a crucial but challenging task in multiagent reinforcement learning (MARL), as it has to deal with the issue that the joint action space increases exponentially with the number of agents in such scenarios. This article proposes an approach, named SMIX(λ), that uses an off-policy training to achieve this by avoiding the greedy assumption commonly made in CVF learning. As importance sampling for such off-policy training is both computationally costly and numerically unstable, we proposed to use the λ-return as a proxy to compute the temporal difference (TD) error. With this new loss function objective, we adopt a modified QMIX network structure as the base to train our model. By further connecting it with the Q(λ) approach from a unified expectation correction viewpoint, we show that the proposed SMIX(λ) is equivalent to Q(λ) and hence shares its convergence properties, while without being suffered from the aforementioned curse of dimensionality problem inherent in MARL. Experiments on the StarCraft Multiagent Challenge (SMAC) benchmark demonstrate that our approach not only outperforms several state-of-the-art MARL methods by a large margin but also can be used as a general tool to improve the overall performance of other centralized training with decentralized execution (CTDE)-type algorithms by enhancing their CVFs.

30 October 2024 in Neural Networks
Verified
Journal Article
Closed access
YLYao Li
Yao Li
YWYuHui Wang
YuHui Wang
XTXiaoyang Tan
Xiaoyang Tan

8 October 2021
Verified
Book Chapter
Closed access
PDF file
YWYuhui Wang
Yuhui Wang
JDJunping Du
Junping Du
YSYingxia Shao
Yingxia Shao
ALAng Li
Ang Li
XXXin Xu
Xin Xu

9 September 2026
Verified
Book Chapter
Closed access
PDF file
WZWenxuan Zhang
Wenxuan Zhang
YWYuhui Wang
Yuhui Wang
DJDonggang Jia
Donggang Jia
XSXiaoqian Shen
Xiaoqian Shen
JDJian Ding
Jian Ding
MEMohamed Elhoseiny
Mohamed Elhoseiny

22 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
DZDeyao Zhu
Deyao Zhu
YWYuhui Wang
Yuhui Wang
JSJuergen Schmidhuber
Juergen Schmidhuber
MEMohamed Elhoseiny
Mohamed Elhoseiny
Offline RL methods have been shown to reduce the need for environment interaction by training agents using offline collected episodes. However, these methods typically require action information to be logged during data collection, which can be difficult or even impossible in some practical cases. In this paper, we investigate the potential of using action-free offline datasets to improve online reinforcement learning, name this problem Reinforcement Learning with Action-Free Offline Pretraining (AFP-RL). We introduce Action-Free Guide (AF-Guide), a method that guides online training by extracting knowledge from action-free offline datasets. AF-Guide consists of an Action-Free Decision Transformer (AFDT) implementing a variant of Upside-Down Reinforcement Learning. It learns to plan the next states from the offline dataset, and a Guided Soft Actor-Critic (Guided SAC) that learns online with guidance from AFDT. Experimental results show that AF-Guide can improve sample efficiency and performance in online training thanks to the knowledge from the action-free offline dataset. Code is available at https://github.com/Vision-CAIR/AF-Guide.