This article was published for PREMIUM members, available by subscription. You can join here in a minute or less. If you're already a member, log-in from the top right menu.

Premium Teaser
Screenshot from 2015-02-10 16:52:26

To Infinity (and NaN?) with Deep Reinforcement Learning in PlanetWars

Alex J. Champandard on March 4, 2015

This tutorial with Spyridon Samothrakis will cover the techniques and tricks for applying Reinforcement Learning using Neural Networks, particularly to the problem of PlanetWars. You'll learn the different approaches for solving the problem, what needs to be done for it to work at all, and how best to tear your hair out when it doesn't work!