Graduated from the University of Alberta with a Ph.D. in Computing Science. My supervisors were Michael Bowling and Joel Veness. I am now a Research Scientist at Google DeepMind. My main research interest is reinforcement learning: representation learning, value function approximation, model learning, exploration, and all those other concepts that we feel are necessary to the development of generally competent agents. I have also recently acquired a (theoretically expensive) taste for universal source coding. I helped develop both the Critterbot and the Arcade Learning Environment. The Critterbot is a reinforcement learning robot built by the Reinforcement Learning and Artificial Intelligence lab at the University of Alberta (I'm the one to blame for any faults in its ARM microcontroller's operating system). The ALE is a more recent project that aims to encourage and catalyze reinforcement research in large, interesting, human-made domains (Atari 2600 games).