Intern
Reinforcement Learning and Computational Decision-Making

Rodrigo Coelho

M.Sc. Rodrigo Coelho

Ph.D. Student
Reinforcement Learning and Computational Decision-Making
Fraunhofer IISB
Schottkystraße 10
91058 Erlangen
Deutschland

About me

I am an external PhD student in the LiteRL group, supervised by Prof. Dr. Carlo D'Eramo, since February 2026. I work at Fraunhofer IISB in the AI-Augmented Simulation group as a researcher focusing on two main topics: the application of Reinforcement Learning in industrial use cases such as power electronics, and the intersection between machine learning and quantum computing.

Before I joined Fraunhofer IISB in December 2023, I completed a Bachelor's and Master's degree in Engineering Physics at the University of Minho, in Braga, Portugal. My master thesis, titled "Tradeoff between moving targets, gradient magnitude and performance in quantum variational Q-Learning", explored how the training instabilities inherent to Q-Learning help with the trainability of variational quantum circuits.

Conferences:
 

  • Medvedev, V., Coelho, R., Erdmann, A., & Rosskopf, A. (2025, November). Inverse Design of Metasurfaces Using Reinforcement Learning Combined with Physics-Informed Neural Networks. In 2025 Photonics & Electromagnetics Research Symposium-Fall (PIERS-Fall) (pp. 1-10). IEEE.
  • Kruse, G., Coelho, R., Rosskopf, A., Wille, R., & Lorenz, J. M. (2025, August). Cleanqrl: Lightweight single-file implementations of quantum reinforcement learning algorithms. In 2025 IEEE International Conference on Quantum Computing and Engineering (QCE) (Vol. 1, pp. 1640-1645). IEEE.
  • Coelho, R., Kruse, G. and Rosskopf, A. (2025). Quantum-Efficient Kernel Target Alignment. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: QAIO; ISBN 978-989-758-737-5; ISSN 2184-433X, SciTePress, pages 763-772. DOI: 10.5220/0013391500003890 
  • Kruse, G., Coelho, R., Rosskopf, A., Wille, R. and Lorenz, J.-M. (2025). Benchmarking Quantum Reinforcement Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: QAIO; ISBN 978-989-758-737-5; ISSN 2184-433X, SciTePress, pages 773-782. DOI: 10.5220/0013393200003890
  • Kruse, G., Coelho, R., Rosskopf, A., Wille, R., & Lorenz, J. M. (2024, September). Hamiltonian-based quantum reinforcement learning for neural combinatorial optimization. In 2024 IEEE International Conference on Quantum Computing and Engineering (QCE) (Vol. 1, pp. 1617-1627). IEEE.
  • Yang, X., Kruse, G., Schwanninger, R., Coelho, R., Wunder, B., Rosskopf, A., ... & Maerz, M. (2024, November). Reinforcement Learning Strategies for Parameter Design of Bidirectional Cllc Resonant Converters With Ultrawide Voltage Range. In 2024 IEEE Design Methodologies Conference (DMC) (pp. 1-7). IEEE.

Journals:

  • Coelho, R., Sequeira, A., & Paulo Santos, L. (2024). Vqc-based reinforcement learning with data re-uploading: performance and trainability. Quantum Machine Intelligence, 6(2), 53.