Noah Dormann
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolNoah Dormann is a Cambridge MPhil student and Computer Science researcher based in Munich with nine years of software engineering experience and a strong foundation in physics, mathematics, and engineering. He focuses on reinforcement learning, exploring its role in AI-enabled scientific discovery and research. Noah contributes to open-source RL tooling—most notably implementing robust save/load functionality and tests in the PyTorch port of Stable Baselines (stable-baselines3), ensuring model and optimizer state persistence. His background from Technische Universität München and early competition success reflect a mix of rigorous academics and hands-on problem solving. He combines research-oriented curiosity with practical ML engineering skills, bridging prototype research and reliable implementation. Colleagues describe him as driven by long-term scientific impact rather than short-term metrics.
10 years of coding experience
Chiemgau-GymnasiumInformatik, Informatik at Technische Universität München
German, English, Spanish
Github Skills (7)
pytorch10
machine-learning10
python10
reinforcement-learning10
tdd9
ppp9
sac9
Programming languages (5)
Github contributions (5)
DLR-RM/stable-baselines3
Nov 2019 - Jun 2020
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:48 commits, 1 PR, 25 pushes in 7 months
Contributions summary:Noah made contributions focused on implementing saving and loading features within the PyTorch-based reinforcement learning library. These changes involved modifying the base class to include functionalities for saving and loading model parameters and optimizer states. Furthermore, the user added tests to verify the save and load capabilities, ensuring the correct functionality and persistence of model weights.
pytorchreinforcement-learningstable-baselinesreinforcement-learning-algorithmsmachine-learning
Artemis-Skade/softlearning
Nov 2020 - Nov 2020
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
Contributions:21 pushes in 3 days
entropydeep-reinforcement-learningtrainingframework-learningactor-critic-algorithm
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.