João Carvalho
Postdoctoral Researcher at Technische Universität Darmstadt
Frankfurt, Hesse, Germany
Summary
👤
Senior🎓
Top SchoolJoão Carvalho is a Postdoctoral Researcher at TU Darmstadt with 11 years of experience bridging electrical engineering and computer science, currently completing a PhD in Computer Science. He focuses on reinforcement learning and control, contributing to MushroomRL by implementing LQR/LQG value and gradient computations, Gaussian policies, batch processing, and test-driven refactors that improved both correctness and readability. His background includes industry software development and engineering roles, giving him practical systems experience alongside rigorous academic research. Trained at Instituto Superior Técnico, the University of Freiburg and with exchange time at TU Delft, he combines European academic breadth with hands-on open-source contributions. Colleagues know him for turning complex control theory into usable, well-tested library code—a blend of theoretical depth and engineering discipline.
11 years of coding experience
11 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at The University of FreiburgTechnischen Universität DarmstadtExchange Student, Electrical and Computer Engineering, Exchange Student, Electrical and Computer Engineering at Delft University of TechnologyMaster of Science - MS, Electrical and Computer Engineering, Master of Science - MS, Electrical and Computer Engineering at Instituto Superior Técnico
Github Skills (9)
python10
reinforcement-learning10
numpy10
pytorch9
algorithms8
data-structures8
algorithm8
data-structure8
testing7
Programming languages (8)
Github contributions (5)
MushroomRL/mushroom-rl
May 2020 - Oct 2020
Python library for Reinforcement Learning.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:20 commits, 6 PRs, 2 comments in 5 months
Contributions summary:João primarily focused on enhancing the LQR (Linear Quadratic Regulator) and LQG (Linear Quadratic Gaussian) functionalities within the reinforcement learning library. Their contributions include adding computations for the Q function, value functions, and gradients related to LQR and LQG problems, including Gaussian policy implementations. They also fixed existing tests and improved the descriptions of the implemented methods, indicating a focus on both functionality and clarity of the library's core algorithms. Further development included adding batch computation and refactoring code for better readability and maintainability.
pytorchpython-librarypythonatariddpg
jacarvalho/nopg
Jan 2020 - Mar 2020
Nonparametric Off-Policy Policy Gradient
Contributions:28 commits, 2 PRs, 23 pushes in 1 month
policynonparametricgradientpolicy-gradientoff-policy
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.