De‐Chuan Zhan

Nanjing University

Papers

1

Total Citations

9

H-Index

1

About

De-Chuan Zhan is a leading researcher in machine learning, with a primary focus on reinforcement learning, multi-task learning, and automated decision-making systems. His most influential work, "Automatic Successive Reinforcement Learning with Multiple Auxiliary Rewards" (2019, 9 citations), addresses a critical challenge in reinforcement learning: the design of effective reward functions. Zhan’s innovative approach introduces a framework that automatically generates and integrates multiple auxiliary rewards to guide an agent’s learning process, significantly improving efficiency and performance in complex applications such as robotics motion, self-driving, and recommendation systems. This contribution has been widely recognized for its practical impact, offering a scalable solution to reward engineering—a long-standing bottleneck in the field. Beyond this, Zhan has made notable strides in multi-task learning, where his work on shared representations and task relationships has advanced the ability of models to learn across diverse domains simultaneously. With a growing citation record and a reputation for bridging theoretical rigor with real-world deployment, Zhan continues to shape the next generation of intelligent systems, making his research essential reading for students and practitioners alike.

Research Focus

Key Achievements

1
H-Index
1
Papers
9
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
Automatic Successive Reinforcement Learning with Multiple Auxiliary Rewards
9 citations · 2019
📈 Most Prolific Year: 2019 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Nanjing University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago