First things first: playing good old Atari games might be cool but whyshould I write a program for doing it? Well teaching a computer to playa game means teaching it to develop strategies and use foresightplanning to solve a certain problem. The tools you gather while solvingi.e. space invaders are the same you may use to solve any problem whichrequires a sequential set of decisions in order to find an optimalsolution to some problem, like i.e. controlling a robot that collectsgarbage. Furthermore, there is a lot of scientific research onreinforcement learning that focuses on solving Atari games which makesit a good starting point, as large amounts of publications and opensource code already exists.What to expect from this talk? At first there will be a very shortintroduction to reinforcement learning theory, just the very basics,common applications and some references for further reading. Next pointsare, how to run Atari games from inside python for a learning task (withOpenAI's gym), and where to find an algorithm for the actual learningproblem. Finally it will be shown how to build it all together in ajupyter notebook and let the algorithm play the game. Et voilà that'syour computer beating you in space invaders.
I would like to work with open source projects to create a branch of the tree with all
of the best videos for your open source project. Please
send me an email if you are interested.