Dianyu Zhong

Dianyu Zhong

Auto-generated profile, based on publicly available information

Dianyu Zhong

Center for Intelligent and Networked Systems (CFINS), Department of Automation and BNRist, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
3 December 2025 in Building and Environment
Verified
Journal Article
Closed access
IRFAN QAISARIRFAN QAISAR
IRFAN QAISAR
KSkailai Sun
kailai Sun
DZDianyu Zhong
Dianyu Zhong
XYXu Yang
Xu Yang
XMXi Miao
Xi Miao
QZQianchuan Zhao
Qianchuan Zhao

5 August 2025 in Energy and Buildings
Verified
Journal Article
Closed access
DZDianyu Zhong
Dianyu Zhong
TXTian Xing
Tian Xing
KSkailai Sun
kailai Sun
ZZZiyou Zhang
Ziyou Zhang
QZQianchuan Zhao
Qianchuan Zhao
Jian KangJian Kang
Jian Kang

22 May 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
DZDianyu Zhong
Dianyu Zhong
YYYiqin Yang
Yiqin Yang
ZZZiyou Zhang
Ziyou Zhang
YJYuhua Jiang
Yuhua Jiang
BXBo XU
Bo XU
QZQianchuan Zhao
Qianchuan Zhao
Entropy regularization is widely used to improve policy optimization and encourage exploration in reinforcement learning. By maximizing both the expected return and entropy, the agent aims to succeed at the task while acting as randomly as possible. However, current methods based on policy entropy encourage the agent to explore diverse actions, but they do not directly promote exploring diverse states. In this study, we theoretically reveal the challenge of optimizing the agent's next-state entropy and the gap between maximum next-state entropy and current policy entropy regularization methods. To address this limitation, we introduce Maximum Next-State Entropy (MNSE), a novel method that maximizes next-state entropy through an action mapping layer following the inner policy. We provide a theoretical analysis demonstrating that MNSE can maximize next-state entropy by optimizing the entropy of the inner policy. We conduct extensive experiments on various continuous control tasks and demonstrate that MNSE can significantly improve the performance of RL algorithms.