About me

Machine Learning Scientist,
lastminute.com, Barcelona, Spain.
Email: juan@martinezpiazuelo.com

I am a Machine Learning Scientist with a background in Automatic Control and Optimization. My work focuses on designing and deploying machine learning models for real-world decision-making systems, combining data-driven methods with principled optimization techniques.

Education:
PhD. Automatic Control Engineering, Universitat Politècnica de Catalunya (UPC), 2024.
M.S. Electronic Engineering, Universidad de los Andes, 2019.
B.S. Electronic Engineering, Universidad de los Andes, 2017.

Research interests:
Machine learning, optimization, game theory, and automatic control.

Publications

For a more up-to-date list of publications please visit my Google Scholar profile.

Books

• J. Martinez-Piazuelo, C. Ocampo-Martinez and N. Quijano, Generalized Nash Equilibrium Seeking in Population Games: Applications in the Control of Large-Scale Multi-agent Systems, Springer Nature, 2026, doi: 10.1007/978-3-032-06081-5. [Publisher]

Journal papers

• J. Martinez-Piazuelo, C. Ocampo-Martinez and N. Quijano, "Distributed Nash equilibrium seeking in strongly contractive aggregative population games," in IEEE Transactions on Automatic Control, vol. 69, no. 7, pp. 4427-4442, 2024, doi: 10.1109/TAC.2023.3321208. [Paper]
• J. Martinez-Piazuelo, W. Ananduta, C. Ocampo-Martinez, S. Grammatico and N. Quijano, "Population games with replicator dynamics under event-triggered payoff provider and a demand response application," in IEEE Control Systems Letters, vol. 7, pp. 3417-3422, 2023, doi: 10.1109/LCSYS.2023.3285532. [Paper]
• A. Sanchez-Amores, J. Martinez-Piazuelo, J. M. Maestre, C. Ocampo-Martinez, E. F. Camacho and N. Quijano, "Coalitional model predictive control of parabolic-trough solar collector fields with population-dynamics assistance," in Applied Energy, vol. 334, pp. 120740, 2023, doi: 10.1016/j.apenergy.2023.120740. [Paper]
• J. Martinez-Piazuelo, C. Ocampo-Martinez and N. Quijano, "On distributed Nash equilibrium seeking in a class of contractive population games," in IEEE Control Systems Letters, vol. 6, pp. 2972-2977, 2022, doi: 10.1109/LCSYS.2022.3182625. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "Nash equilibrium seeking in full-potential population games under capacity and migration constraints," in Automatica, vol. 141, pp. 110285, 2022, doi: 10.1016/j.automatica.2022.110285. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "A payoff dynamics model for generalized Nash equilibrium seeking in population games," in Automatica, vol. 140, pp. 110227, 2022, doi: 10.1016/j.automatica.2022.110227. [Paper]
• J. Martinez-Piazuelo, G. Diaz-Garcia, N. Quijano and L. F. Giraldo, "Discrete-time distributed population dynamics for optimization and control," in IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 11, pp. 7112-7122, Nov. 2022, doi: 10.1109/TSMC.2022.3151042. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "Decentralized charging coordination of electric vehicles under feeder capacity constraints," in IEEE Transactions on Control of Network Systems, vol. 9, no. 4, pp. 1600-1610, Dec. 2022, doi: 10.1109/TCNS.2021.3128498. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "A payoff dynamics model for equality-constrained population games," in IEEE Control Systems Letters, vol. 6, pp. 530-535, 2022, doi: 10.1109/LCSYS.2021.3082865. [Paper]
• J. Martinez-Piazuelo, D. E. Ochoa, N. Quijano and L. F. Giraldo, "A multi-critic reinforcement learning method: an application to multi-tank water systems," in IEEE Access, vol. 8, pp. 173227-173238, 2020, doi: 10.1109/ACCESS.2020.3025194. [Paper]

Conference papers

• N. Mignoni, J. Martinez-Piazuelo, R. Carli, C. Ocampo-Martinez, N. Quijano and M. Dotoli, "A game-theoretical control framework for transactive energy trading in energy communities," in Proceedings of the 22nd IEEE European Control Conference (ECC), 2024, pp. 786-791, doi: 10.23919/ECC64448.2024.10591157. [Paper]
• J. Martinez-Piazuelo, C. Ocampo-Martinez, N. Quijano and A. Ingimundarson, "Microalgae production and maintenance optimization via mixed-integer model predictive control," in Proceedings of the 22nd IFAC World Congress, 2023, IFAC-PapersOnLine, vol. 56, no. 2, pp. 11100-11105, ISSN 2405-8963, doi: 10.1016/j.ifacol.2023.10.819. [Paper]
• A. Sánchez-Amores, J. Martinez-Piazuelo, J. M. Maestre, C. Ocampo-Martinez, E. F. Camacho and N. Quijano, "Population-dynamics-assisted coalitional model predictive control for parabolic-trough solar plants," in Proceedings of the 22nd IFAC World Congress, 2023, IFAC-PapersOnLine, vol. 56, no. 2, pp. 7710-7715, ISSN 2405-8963, doi: 10.1016/j.ifacol.2023.10.1174. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "Búsqueda de equilibrios de Nash en juegos poblacionales bajo información parcial y su aplicación en juegos de congestión," en XLIII Jornadas de Automática: libro de actas, 2023, pp. 317-322. doi: 10.17979/spudc.9788497498609.317. [Paper]
• J. Martinez-Piazuelo, G. Obando, N. Quijano and C. Ocampo-Martinez, "Distribución dinámica de recursos vía juegos poblacionales y modelos dinámicos de pago," en XLIII Jornadas de Automática: libro de actas, 2022, pp. 392-399. doi: 10.17979/spudc.9788497498418.0392. [Paper]
• J. Martinez-Piazuelo, C. Ocampo-Martinez and N. Quijano, "Generalized Nash equilibrium seeking in population games under the Brown-von Neumann-Nash dynamics," in Proceedings of the 20th IEEE European Control Conference (ECC), 2022, pp. 2161-2166, doi: 10.23919/ECC55457.2022.9838437. [Paper]
• J. Martinez-Piazuelo, N. Quijano and C. Ocampo-Martinez, "Decentralized charging coordination of electric vehicles using multi-population games," in Proceedings of the 59th IEEE Conference on Decision and Control (CDC), 2020, pp. 506-511, doi: 10.1109/CDC42340.2020.9304437. [Paper]
• J. Martinez-Piazuelo, G. Diaz-Garcia, N. Quijano and L. F. Giraldo, "Distributed formation control of mobile robots using discrete-time distributed population dynamics," in Proceedings of the 21st IFAC World Congress, 2020, IFAC-PapersOnLine, vol. 53, no. 2, pp. 3131-3136, ISSN 2405-8963, doi: 10.1016/j.ifacol.2020.12.1049. [Paper]

Additional Projects

• popgames: popgames is an open-source Python package for modeling and simulating generalized Nash equilibrium problems (GNEPs) in population games. The package accompanies my book "Generalized Nash Equilibrium Seeking in Population Games" and serves as a computational framework for experimentation and reproducible research in large-scale multi-agent systems. Code: GitHub Repository | Documentation: Project Website



• Driver drowsiness detection system using convolutional neural networks: In this project, I developed a drowsy driver detection system using a convolutional neural network (CNN) built with TensorFlow. The system is designed to detect the driver's face, accurately locate the eyes, and determine whether the eyes are open or closed. By continuously monitoring the driver’s eye state, the system can assess drowsiness in real-time, helping to prevent accidents caused by fatigue.
  
  
  
  
  
• Distributed formation control of mobile robots: In this project, I developed a distributed control system for coordinating the positions of multiple mobile robots (e-puck v2). Each robot utilizes camera feedback to determine its own position and communicates with other robots in the group to collaboratively achieve the desired formation. This approach enhances flexibility and efficiency in multi-robot systems.
  
  
  
  
  
• Ball-on-beam automatic control system: In this project, I designed and implemented a ball-on-beam control system, integrating an automatic controller to manage the position of the ball. The system utilizes camera video feedback to accurately track the ball's position, enabling precise control and stabilization on the beam.
  
  
  
  
  
• Multi-agent deep reinforcement learning: In this project, I trained reinforcement learning agents for a multi-agent pursuit and evasion game set in a grid world. The agents utilize a Deep Q-Learning algorithm, enhanced by a sequential training strategy designed to promote cooperation among the agents. This approach effectively fosters collaborative behaviors, enabling improved performance in the pursuit and evasion scenarios.
  
  
  
  
  

Contact me

Feel free to reach out to me via email or connect with me on LinkedIn.