How to Train your Decision-Making AIs

The combination of deep learning and decision learning has led to several impressive stories in decision-making AI research, including AIs that can play a variety of games (Atari video games [11], board games [13], complex real-time strategy game Starcraft II [17]), control robots (in simulation and in the real world), and even fly a weather balloon [1]. These are examples of sequential decision tasks, in which the AI agent needs to make a sequence of decisions to achieve its goal.