Summary
In this chapter, we discussed the model-based approach to RL and implemented one of the recent research architectures from DeepMind, which augments the model of the environment into the model-free agents. This model tries to join both model-free and model-based paths into one, to allow the agent to decide which knowledge to use.
In the upcoming chapter (which will be the last in the book), we'll take a look at a recent DeepMind breakthrough in the area of full-information games: the AlphaGo Zero algorithm.