Atanas joined argmax.ai in May 2017. In 2018 he obtained his MSc in Computer Science from the Technical University of Munich. His Master's thesis dealt with the probabilistic modelling and exploration of spatial environments. He is now pursuing a PhD in the research lab, seeking principled ways to imparting structure to Bayesian models and incentivising explorative behaviour with the help of information theory.
- approximate inference in probabilistic models
- intrinsic motivation
- exploration and modelling of spatial environments
- decision making under uncertainty
- implicit variational families