Yi Su
Principal Research Engineer at Apple
Cupertino, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYi Su is a Principal Research Engineer based in Cupertino with 11 years of industry experience building and deploying advanced machine learning and reinforcement learning systems. He combines deep academic training (PhD and MSE from Johns Hopkins, CS degrees from Tsinghua) with practical impact at companies including Apple, Ant Group and Nuance, progressing from research scientist to principal engineering roles. His open-source contributions to the popular tianshou PyTorch RL library—adding algorithms like CQL, CRR, IQN, FQF, Rainbow DQN and GAIL—highlight a hands-on focus on modern RL methods and reproducible benchmarks in Atari environments. Comfortable bridging research and production, he brings a track record of shipping novel algorithms into real products and experimental platforms.
11 years of coding experience
13 years of employment as a software developer
Johns Hopkins UniversityComputer Science and Technology, Computer Science and Technology at Tsinghua University
English, Chinese
Github Skills (9)
machine-learning10
ata10
atari260010
ml10
pytorch7
ppp3
sac3
imitation-learning3
tdd3
Programming languages (4)
Github contributions (5)
thu-ml/tianshou
May 2021 - Dec 2022
An elegant PyTorch deep reinforcement learning library.
Role in this project:
ML Engineer
ML EngineerContributions:68 reviews, 20 commits, 22 PRs in 1 year 7 months
Contributions summary:Yi contributed significantly to the implementation of various deep reinforcement learning algorithms and techniques within the tianshou library. Their work involved adding new algorithms such as discrete Conservative Q-Learning (CQL), Critic Regularized Regression (CRR), Implicit Quantile Network (IQN), Fully-parameterized Quantile Function (FQF), Rainbow DQN, and Generative Adversarial Imitation Learning (GAIL). This included modifying existing code, creating new example files, and adjusting parameters for these algorithms within the context of Atari environments, indicating a focus on developing and experimenting with RL models.
deep-reinforcement-learningbenchmarknpgtd3reinforcement
nuance1979/srilm-python
Feb 2015 - Jan 2022
Python binding for SRI Language Modeling Toolkit implemented in Cython
Contributions:2 releases, 179 commits, 3 PRs in 7 years
pythonagent-based-modelingpython-bindingmodeling-languagecython
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.