Module 7: Reinforcement Learning

Topic 4: RL and Games

Using RL to train powerful AI game players

This topic is pretty quick since we have discussed alpha go before briefly as well as each of the components of Alpha Go.  What I am focusing on here is an overview of how RL, minimax, MCTS, and deep learning (we cover deep learning in the next module!) can be combined for a super powerful gaming agent.

Link to my slides