Zhenyu Tan

Papers

Total Citations

H-Index

About

Zhenyu Tan is a robotics researcher whose work sits at the intersection of deep reinforcement learning and legged locomotion, tackling one of the most persistent challenges in robotics: enabling legged robots to walk reliably in real-world environments. His most recognized contribution, the 2020 paper "Learning to Walk in the Real World with Minimal Human Effort" (76 citations), addresses a critical bottleneck in applying deep RL to physical robotic systems — the need for extensive human supervision during training. By developing systems that allow legged robots to autonomously acquire locomotion policies with minimal intervention, Tan's research significantly lowers the barrier between simulation-based learning and practical deployment. This work represents a meaningful step toward autonomous robot learning pipelines that can operate outside controlled laboratory settings. His contributions resonate strongly within the robotics and machine learning communities, where the sim-to-real transfer problem remains an active and challenging frontier. For students and researchers exploring autonomous robot control, reinforcement learning for physical systems, or legged robot locomotion, Tan's work offers both technical rigor and practical relevance as a foundational reference point.