Biography:
Claudia Domínguez Barbero is a member of IIT-Comillas as administrative and service staff (PAS). Her role focuses on advancing research activities both broadly and at a more specific level across the Institute. Her responsibilities include providing support in niche research technologies, contributing to institutional technology strategy, capturing research-related technological requirements and needs, and delivering training in cutting-edge academic and professional technologies, among others. Claudia was born in Toledo in 1993. She obtained her PhD in 2026 from Universidad Pontificia Comillas – ICAI, with a focus on Deep Reinforcement Learning (DRL) applied to the optimal control of isolated microgrids. She holds a Bachelor’s degree in Computer Engineering (specialization in computing) from Universidad de Castilla – La Mancha (Albacete, 2016), and a Master’s degree in Research in Artificial Intelligence (specialization in automated reasoning) from Universidad Internacional Menéndez Pelayo (2017).
Areas of interest:
Reinforcement learning, natural language processing, deep learning, and other techniques of modeling, optimization, reasoning, planning and prediction.
Experience:
She worked for 18 months at Medsavana S.L. as a developer in natural language processing applied to the medical field. In addition, she worked on several projects at Comillas, at the Institute for Research in Technology (IIT), on predictive maintenance in high-voltage power networks while pursuing her PhD. She also has teaching experience at Universidad Pontificia Comillas, as a lab instructor in C programming courses (3 semesters) and algorithm design (1 semester) for undergraduate students, and as the main instructor, also in algorithm design, for exchange students (SAPIENS program). She has also provided training for 7 years in Introduction to Python for PhD students as part of a training program.
Skills:
DRL, NLP, DL, ML, data analysis, processing, storing and retrieval. Computer engineer related skills (databases, web aplication design and backend, APIs, software distribution and licenses, good design patterns). Python language (4-5 years of experience) with libraries mainly ML and visualization related (2-3 years of experience). General algorithm design and optimization (tree search, graph search, combinatorial optimization, linear optimization, dynamic programming, meta-heuristics, planning) and optimization advanced tools (data structures, parallelization and concurrence, profiling, debugging). Knowledge in statistics and linear algebra mainly, but also game theory, graph theory and others. LaTeX, Linux, Git.
JCR-JIF: 9,300 Q1 (2025) - SJR: 2,516 Q1 (2025) 
C. Domínguez-Barbero, J. García-González, M.A. Sanz-Bobi, A. García-Cerrada, "Energy management of a microgrid considering nonlinear losses in batteries through Deep Reinforcement Learning", Applied Energy, Vol. 368, pp. 123435, August 2024. [Online: May 2024] doi: 10.1016/j.apenergy.2024.123435
JCR-JIF: 11,000 Q1 (2024); 12,200 Q1 (2025) - SJR: 2,902 Q1 (2024); 2,864 Q1 (2025) C. Domínguez-Barbero, J. García-González, M.A. Sanz-Bobi, "Twin-delayed deep deterministic policy gradient algorithm for the energy management of microgrids", Engineering Applications of Artificial Intelligence, Vol. 125, pp. 106693, October 2023. [Online: July 2023] doi: 10.1016/j.engappai.2023.106693
JCR-JIF: 7,500 Q1 (2023); 9,000 Q1 (2025) - SJR: 1,749 Q1 (2023); 1,782 Q1 (2025) C. Domínguez-Barbero, J. García-González, M.A. Sanz-Bobi, E.F. Sánchez-Úbeda, "Optimising a microgrid system by deep reinforcement learning techniques", Energies, Vol. 13, nº. 11, pp. 2830, June 2020. [Online: June 2020] doi: 10.3390/en13112830
JCR-JIF: 3,004 Q3 (2020); 3,900 Q3 (2025) - SJR: 0,598 Q2 (2020); 0,748 Q1 (2025) 
