User Tools

Site Tools


Pedro A. Ortega

Research Scientist
Google DeepMind

This is Ludwig Boltzmann (no joke). Thanks Jordi!


I am a Research Scientist in the AI Safety Group at DeepMind. My research focuses on the formal principles of intelligent systems 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

Free Energy Functional (it's also meant to be a puzzling pic)

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.

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. Check out its members' sites:

Travel Schedule

Date Where Title
Jan 6-8, 2017 Pacific Grove, California Beneficial AI 2017
Jan 25, 2017 FHI, Oxford -
Mar 3, 2017 FHI, Oxford -
Mar 17-26, 2017 Philadelphia -
May 12, 2017 Columbia University, New York Talk at Information Processing and Behavioral Variability

News (on Twitter)

Timeline of @AdaptiveAgents

AdaptiveAgents avatar

A relational logic for higher-order programs
About 4 hours, 7 mins ago by: Pedro A. Ortega (@AdaptiveAgents)

AdaptiveAgents avatar

Learned Optimizers that Scale and Generalize
About 10 hours, 7 mins ago by: Pedro A. Ortega (@AdaptiveAgents)

AdaptiveAgents avatar

Statistical Mechanical Analysis of Online Learning with Weight Normalization in Single Layer Perceptron
About 1 day, 4 hours ago by: Pedro A. Ortega (@AdaptiveAgents)

AdaptiveAgents avatar

Andrew Ng is leaving Baidu in search of a grander AI challenge
About 1 day, 8 hours ago by: Pedro A. Ortega (@AdaptiveAgents)

AdaptiveAgents avatar

Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
About 1 day, 10 hours ago by: Pedro A. Ortega (@AdaptiveAgents)


Pedro A. Ortega
Google UK
DeepMind 6th Floor
6 Pancras Square
London N1C 4AG

home.txt ยท Last modified: 2017/03/09 19:45 by peortega

Page Tools