Paper presented @ IROS 2017: An Information-Theoretic On-Line Update Principle for Perception-Action Coupling
Peng Z, Genewein T, Leibfried F, Braun DA (2017). An Information-Theoretic On-Line Update Principle for Perception-Action Coupling.
I am a research scientist at DeepMind, working on AI safety. Prior to that I worked in the Deep Learning Perception group at the Bosch Center for Artificial Intelligence on Bayesian deep learning and neural network compression. I did my PhD at the Sensorimotor Learning and Decision-Making research group lead by Daniel A. Braun at the Max Planck Institute for Intelligent Systems and the Max Planck Institute for Biological Cybernetics. My PhD research has been focused on understanding how decision-makers can leverage the structure of their environment in order to efficiently cope with uncertainty. I investigated links between bounded rationality (lately termed computational rationality) and information theory, in particular rate distortion theory.
Content outdated: The publication list, some of the content and my CV are currently a bit outdated. For an up-to-date publication list please refer to my Google Scholar profile page.
Peng Z, Genewein T, Leibfried F, Braun DA (2017). An Information-Theoretic On-Line Update Principle for Perception-Action Coupling.
Talk at Amlab (Max Welling) / UvA-Bosch Delta Lab (Zeynep Akata) on Information-optimal coupling of perception and action through lossy compression.
I have successfully defended my PhD thesis which concludes my PhD.
Metzen JH, Genewein T, Fischer V, Bischoff B (2017). On Detecting Adversarial Perturbations.
Grau-Moya J, Leibfried F, Genewein T, Braun D.A. Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes