Chang Ye
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolChang Ye is a software engineer based in Sunnyvale, California with nine years of experience and currently on Google's engineering team. He specializes in machine learning and reinforcement learning tooling, with notable open-source contributions to cleanRL where he implemented and refactored intrinsic curiosity modules, integrated Random Network Distillation (RND) into PPO, and added visualization and environment-interaction support. Chang excels at bridging research and production by turning research-friendly, single-file algorithm implementations into maintainable, experiment-ready code. His work demonstrates a practical focus on developer ergonomics and reproducible RL experimentation while handling complex model integrations in established codebases.
9 years of coding experience
4 years of employment as a software developer
Computer Science, Computer Science at Dalhousie UniversityMaster of Science - MS, Computer Science, 3.778, Master of Science - MS, Computer Science, 3.778 at New York UniversityBachelor of Engineering - BE, Computer Software Engineering, Bachelor of Engineering - BE, Computer Software Engineering at Zhejiang University of Technology
English, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (13)
gymnasium10
open-ai-gym10
deep-reinforcement-learning10
pytorch10
machine-learning10
ppp10
deep-learning10
python10
deep-learning-ai10
reinforcement-learning10
wandb5
ata4
atari26004
Programming languages (5)
Github contributions (5)
vwxyzjn/cleanrl
Jul 2020 - Aug 2022
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Role in this project:
ML Engineer
ML EngineerContributions:48 reviews, 30 commits, 5 PRs in 2 years 1 month
Contributions summary:Chang primarily contributed to the implementation and refactoring of intrinsic curiosity models within the cleanRL repository, focusing on Reinforcement Learning (RL) algorithms. Their work involved integrating Random Network Distillation (RND) into the Proximal Policy Optimization (PPO) algorithm, including the development of RND model components and integrating with the existing codebase. The contributions also included adding visualization tools and making updates to support environment interactions.
pythondeep-reinforcement-learninggomokutd3reinforcement
yooceii/Rotation-Translation-and-Cropping-for-Zero-Shot-Generalization
Nov 2019 - Apr 2022
Contributions:16 commits, 5 pushes, 5 comments in 2 years 6 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.