Tian-qing Chang
Papers
1
Total Citations
5
H-Index
1
About
Tian-qing Chang is a researcher advancing the frontiers of reinforcement learning and robotic control, with a focus on sample efficiency and policy robustness. His most-cited work, "A policy optimization algorithm based on sample adaptive reuse and dual-clipping for robotic action control" (2022), introduces a novel method that intelligently reuses past experiences while employing dual-clipping mechanisms to stabilize training. This contribution directly addresses a critical bottleneck in deep reinforcement learning: the trade-off between sample efficiency and policy performance in real-world robotic tasks. By enabling more reliable and data-efficient learning, Chang’s algorithm has garnered 5 citations, laying a foundation for scalable autonomous systems. His research sits at the intersection of optimization theory and practical robotics, aiming to bridge the gap between simulated training and physical deployment. Chang’s work is particularly notable for its emphasis on adaptive reuse, a concept that reduces the need for costly real-world data collection. For students and researchers exploring sample-efficient policy learning, his contributions offer a pragmatic path toward more robust and deployable robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1