I am an MRes student in Computational Statistics and Machine Learning at University College London advised by Tim Lillicrap and Karl Friston. I am also a student researcher at Vincent Vanhoucke’s robotics group at Google Brain.
My goal is to build intelligent machines based on concepts of the human brain, and evaluate them in complex simulations. Currently, I’m especially interested in model based exploration and learning hierarchical behavior. If you have any questions, feel free to contact me at [email protected].
2018-02-16 Guest lecture at Stanford CS 20 on Variational Inference in TF.
2018-02-14 Talk at IBM Research AI on ThalNet.
2018-02-05 Paper submitted to RSS 2018.
Please see my Scholar profile for a full list including article links.
TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow (ArXiv)
D Hafner, J Davidson, V Vanhoucke
Learning Hierarchical Information Flow with Recurrent Neural Modules (NIPS 2017)
D Hafner, A Irpan, J Davidson, N Heess
Probabilistic Routing for On-Street Parking Search (ESA 2016)
T Arndt, D Hafner, T Kellermeier, S Krogmann, A Razmjou, M Krejca, R Rothenberger, T Friedrich
Deep Reinforcement Learning from Raw Pixels in Doom (BSc thesis)
TensorFlow in Action (Manning, in progress)
H Nguyen, D Hafner
TensorFlow for Machine Intelligence (Bleeding Edge Press)
S Abrahams, D Hafner, E Erwitt, A Scarpinelli
Danijar Hafner a graduate student at University College London under the supervision of Tim Lillicrap and Karl Friston. He is also an intern with the robotics group at Google Brain, where he developed the brain-inspired sequence model ThalNet and the reinforcement learning library TensorFlow Agents. Danijar Hafner co-authored the book “TensorFlow for Machine Intelligence” and guest lectured in Stanford’s course “TensorFlow for Deep Learning Research”. He completed his bachelor’s thesis on deep reinforcement learning for the video game Doom at the Hasso Plattner Institute, Germany.