Fangyu Wu
Postdoctoral Researcher at Columbia University
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolFangyu Wu is a postdoctoral researcher based in New York with 11 years of experience at the intersection of reinforcement learning, computer vision, and control theory, holding a PhD and MEng from UC Berkeley. He has blended academic rigor with industry exposure through internships at NVIDIA and Intel and research roles at Cornell and Columbia, focusing on practical RL systems for control applications. As a contributor to the flow-project, he strengthened a reinforcement-learning traffic control framework by building evaluation leaderboards, visualization tooling, and robust unit tests—improving reproducibility and code quality. Beyond research, he brings a creative sensibility as a part-time photographer and cellist, hinting at a disciplined yet experimental approach to problem solving.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Electrical Engineering and Computer Sciences, Doctor of Philosophy - PhD, Electrical Engineering and Computer Sciences at University of California, BerkeleyUniversity of Illinois Urbana-Champaign
Github Skills (6)
automated-tests10
python10
reinforcement-learning10
testing10
unit-testing8
pyglet8
Programming languages (8)
Github contributions (5)
flow-project/flow
Aug 2018 - Aug 2019
Computational framework for reinforcement learning in traffic control
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:230 commits, 24 PRs, 248 pushes in 1 year
Contributions summary:Fangyu primarily contributed to the development of utilities and automated testing procedures within the reinforcement learning framework. They implemented a leaderboard utility to evaluate policy performance using predefined benchmarks. The user also added versioning information, addressed PEP style violations, and fixed minor bugs throughout the codebase. Additionally, the user integrated a Pyglet renderer for visualization purposes and included unit tests for crucial components, boosting overall code coverage and quality.
autonomousreinforcement-learningvehicle-controldeep-reinforcement-learningbenchmark
fywu85/mampc
Feb 2021 - Jul 2022
Contributions:15 commits, 18 pushes, 2 branches in 1 year 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.