Google DeepMind has developed a successful computer program Alpha Go.
The following technical papers describe techniques underlying the recent success of
Alpha Go program. Some of the concepts and ideas behind these techniques are
to be introduced in this course.
Human-level control through deep reinforcement learning, published in Nature, 2015, Feb 26; vol 518 (N7540), pages 529-33, Feb 26, 2015.
Mastering the game of Go with deep neural networks and tree search, published in Nature, vol 529 (N7587), pages 484-489, Jan 28, 2016.