Xingdong Zuo
Research Engineer at NAVER Corp
Seongnam-si, South Korea
Summary
👤
Senior🎓
Top SchoolXingdong Zuo is a Research Engineer at NAVER Corp with 10 years of experience building scalable reinforcement learning and recommender systems that optimize long-term user engagement. He combines production-focused engineering—deploying retrieval, reranking, and autobidding models at million-user scale—with cutting-edge research in offline RL, having co-authored a NeurIPS 2023 paper and prototyped RLHF solutions. His contributions to widely used open-source tools like OpenAI Gym show practical full-stack skills in RL environments and augmentations (e.g., FrameStack, GrayScaleObservation). Beyond online services, he explores physical AI and learning-based robotic manipulation, reflecting a rare cross-domain interest in both digital decision systems and real-world adaptation.
10 years of coding experience
Master of Science - MS, Machine Learning, Master of Science - MS, Machine Learning at The University of FreiburgBachelor of Science (B.S.), Applied Mathematics, Bachelor of Science (B.S.), Applied Mathematics at Linnaeus University
English, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
openai10
wrapper10
python10
reinforcement-learning10
numpy10
enviroment9
environ9
dev-environment9
environmental9
atari26008
ata8
testing7
Programming languages (12)
Github contributions (5)
openai/gym
Sep 2018 - Sep 2021
A toolkit for developing and comparing reinforcement learning algorithms.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:52 commits, 63 PRs, 90 comments in 3 years
Contributions summary:Xingdong primarily contributed to the `gym` project, a toolkit for reinforcement learning. Their work included modifications to existing environment files, specifically updating and deleting files related to spaces and core functionalities. Furthermore, the user integrated a variety of wrappers, including new features like `GrayScaleObservation`, `ClipAction`, and `FrameStack`, which indicates a focus on enhancing the toolkit's capabilities. The user also updated documentation and other supporting files, indicating a well-rounded approach to the project.
reinforcement-learning
StanfordVL/lagom
Dec 2017 - May 2019
lagom: A light PyTorch infrastructure to quickly prototype reinforcement learning algorithms.
Contributions:560 commits in 1 year 4 months
lagompytorchreinforcement-learning
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.