My goal is to understand human thinking by developing neuroscience-inspired learning algorithms and evaluating them in complex simulations. I'm currently an intern with Google Brain, and MRes student in Computational Statistics and Machine Learning at UCL, London. Previously, I developed Thalamus Gated Recurrent Modules, released the TensorFlow Agents framework, guest lectured at Stanford's CS 20SI TensorFlow course, and completed my bachelor's thesis on deep reinforcement learning in the Doom video game.
Danijar Hafner, Alex Irpan, James Davidson, Nicolas Heess
arXiv preprint arXiv:1709.02878 (2017)