YuanBo Jiang

Mr. YuanBo Jiang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
12 June 2024 in Applied Soft Computing
Verified
Journal Article
Closed access
JWJin Wang
Jin Wang
LGLan Guo
Lan Guo
YJYuanBo Jiang
YuanBo Jiang
SZShengjie Zhang
Shengjie Zhang
QZQingguo Zhou
Qingguo Zhou

12 November 2025 in Journal of Industrial Information Integration
Verified
Journal Article
Closed access
JWJin Wang
Jin Wang
LSLirong Song
Lirong Song
Jun ShenJun Shen
Jun Shen
BYBinbin Yong
Binbin Yong
XHXiaoteng Han
Xiaoteng Han
QZQIngguo Zhou
QIngguo Zhou

13 April 2026 in Information
Verified
Journal Article
Open access
PDF file
YZYu Zhou
Yu Zhou
XGXinYu Guo
XinYu Guo
YJYuanBo Jiang
YuanBo Jiang
JFJiaxuan Fang
Jiaxuan Fang
JWJin Wang
Jin Wang
Kuan-Ching LiKuan-Ching Li
Kuan-Ching Li
Optimizing long-term user satisfaction in sequential recommender systems is a critical challenge. Offline reinforcement learning (RL) offers a promising solution by learning recommendation policies from historical interaction logs without incurring the high costs of online exploration. However, offline RL suffers from severe distribution shift: the learned policy often overestimates the value of out-of-distribution (OOD) items, leading to unreliable recommendations and compromising user satisfaction. To address this issue, we propose a novel framework known as the Q-Learning Regularized Decision Transformer (QRDT). Built upon the Decision Transformer architecture, QRDT models recommendations as a sequence prediction task to capture complex user interest dynamics. To mitigate distribution shift, the QRDT integrates Kullback–Leibler (KL) divergence and maximum entropy regularization into the Q-value function, enabling conservative long-term value estimation while encouraging diverse exploration within the logged data distribution. Extensive experiments on four real-world Amazon e-commerce datasets (CDs, Clothing, Cellphones, and Beauty) demonstrate that the QRDT achieves competitive performance and outperforms the PGPR baseline in most scenarios. Specifically, the proposed method yields improvements of 2.99% in Hit Rate (HR), 2.19% in Normalized Discounted Cumulative Gain (NDCG), 0.94% in Recall, and 0.84% in Precision, verifying the effectiveness of our regularization approach.