Papers
1
Total Citations
6
H-Index
1
About
Zelin Deng is a researcher at the forefront of reinforcement learning and robotics, with a focused expertise in reward shaping for dexterous manipulation. His most-cited work, "Reward shaping in reinforcement learning for robotic hand manipulation" (2025), has already garnered 6 citations, signaling early impact in a rapidly evolving field. Deng’s primary contribution lies in designing sophisticated reward functions that guide robotic hands to learn complex, human-like grasping and manipulation tasks more efficiently—a critical step toward autonomous systems capable of handling delicate or irregular objects. By addressing the sparse-reward problem, his research bridges the gap between simulated training and real-world robotic dexterity. Though early in his career, Deng’s work has been recognized for its practical implications in manufacturing, prosthetics, and assistive robotics. His approach not only accelerates learning but also improves the safety and reliability of robotic interactions. As a rising voice in reinforcement learning, Deng continues to push the boundaries of how machines acquire fine motor skills, making his research essential reading for students and engineers working on next-generation robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Reward shaping in reinforcement learning for robotic hand manipulation6 citations · 2025