Pedro A. Ortega

AGI and Cybernetics Researcher


I was VP of research at Kosen Labs and prior to that, lead of the Safety Analysis Team at DeepMind. My research focuses on artificial general intelligence and the formal principles of intelligence, covering aspects such as learning, planning and decision making in both machines and biological organisms. My approach lies at the intersection between machine learning, computational neuroscience, theoretical economics, and physics.

Research Interests

Most of my work centers on information-theoretic and statistical mechanical approaches to learning and control, leading to contributions in bounded rationality models and recasting adaptive control as a causal inference problem. I have also worked on causal induction, and on game- and decision-theoretic models in computational neuroscience.

Free energy

To get a sense of my work, please refer to:

I was part of the former Tuebingen group on Sensorimotor Learning and Decision Making, where some of the now widespread ideas on Thompson sampling, causality, and thermodynamic methods for reinforcement learning have originated.


Feb 4, 2024 Panel speaker at the Warwick AI Safety Summit 2024, 17 February 2024.
Nov 22, 2023 New website!
Nov 14, 2023 Talk on information-theoretic bounded rationality at the Oxford AI Society.

Selected publications

  1. A minimum relative entropy principle for learning and acting
    Pedro A Ortega, and Daniel A Braun
    Journal of Artificial Intelligence Research, 2010
  2. Thermodynamics as a theory of decision-making with information-processing costs
    Pedro A Ortega, and Daniel A Braun
    Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2013
  3. Meta-learning of sequential strategies
    Pedro A Ortega, Jane X Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, and  others
    arXiv preprint arXiv:1905.03030, 2019
  4. Shaking the foundations: delusions in sequence models for interaction and control
    Pedro A Ortega, Markus Kunesch, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Joel Veness, Jonas Buchli, Jonas Degrave, Bilal Piot, Julien Perolat, and  others
    arXiv preprint arXiv:2110.10819, 2021
  5. Neural networks and the chomsky hierarchy
    Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, and P.A. Ortega
    In International Conference on Learning Representations (ICLR), 2023