Zhiwei Shang
Papers
1
Total Citations
24
H-Index
1
About
Zhiwei Shang is a researcher advancing the frontiers of reinforcement learning (RL), with a focus on developing algorithms that are both stable and sample-efficient for continuous action spaces. His most impactful work, "Relative Entropy Regularized Sample-Efficient Reinforcement Learning With Continuous Actions" (2023), has garnered 24 citations and introduces a novel approach called continuous dynamic policy programming (CDPP). This method addresses critical challenges in modern RL by extending relative entropy regularization to continuous domains, effectively balancing exploration and exploitation while improving learning stability. Shang’s contributions are particularly significant for real-world applications where data is scarce and actions must be smooth, such as robotics and autonomous control. By tackling the dual problems of sample efficiency and algorithmic stability, his work provides a practical foundation for deploying RL in complex, high-dimensional environments. As a rising voice in the field, Shang’s research continues to influence the development of more robust and efficient learning systems, making him a notable figure for students and researchers interested in the future of intelligent decision-making.
Research Focus
Key Achievements
Top Papers
- 1