For many years, researchers have sought methods that can both learn a model that explains their environment, and can then use that model to plan the best course of action. Until now, most approaches have struggled to plan effectively in domains, such as Atari, where the rules or dynamics are typically unknown and complex.


Impressive(said in a Quake 3 voice)! Well, step by step, bit by bit. When will it be able to play in CS or Q3?