Feiyang

Wu Fei Yang, “woo-FAY-yahng” 🔊
ML PhD student at Georgia Tech

feiyangwu@gatech.edu
Linkedin | X | GitHub

My research interests lie in the intersection of optimization, reinforcement learning, and robotics. I develop algorithms to efficiently train robots, ideally with theoretical guarantee.

I am co-advised by Prof. Anqi Wu and Prof. Ye Zhao at Georgia Tech. Additionally, I had the privilege to collaborate with Prof. George Lan on stochastic optimization and RL.

Projects

Learn to Teach at Sea

Field testApr 2026

Digit running the L2T policy zero-shot in the mission bay of the Navy’s Stiletto, including underway at up to 22 knots.

BlogProject

Humanoid Locomotion on Granular Terrain

arXiv 2026

Granular contact physics and terrain-adaptive reinforcement learning for humanoid locomotion.

ProjectarXivBlog

Learn to Teach

RA-L 2025ICRA 2026 Oral

One-stage privileged teacher-student learning for sample-efficient Digit locomotion over 12+ terrain and disturbance settings.

ProjectarXivVideoField test

SEEC: Stable End-Effector Control

ICRA 2026

Model-enhanced residual learning for stable end-effector control during humanoid loco-manipulation.

ProjectarXiv

RL-augmented Adaptive MPC

ICRA 2026

RL corrections to adaptive MPC so bipedal locomotion stays accurate on challenging terrain.

ProjectarXiv

Distributional Inverse Reinforcement Learning

ICML 2026 Oral

Distributional IRL that recovers reward and return distributions for risk-aware imitation.

arXiv

Publication

Reinforcement Learning

Computer Vision