Making Dropout Work with PPO
Vanilla dropout doesn't work with policy gradient methods like PPO, so let's add some flavor to it.
Reinforcement Learning |NaN Recipes
If you got NaN problems
Hello World!
A blog is born, but let's talk some meta first: what's this blog about (boring machine learning), why was it created (learning by explaining), and who's doing the writing (moi).
About |
Building a Game AI for Clash Royale
How and why to teach a ResNet to play mobile games – talk given at Helsinki Data Science meetup
Talk |
Card Targeting in Clash Royale
Making of everyday eventfulness for live ops – talk given at Games First Helsinki
Talk |
Boom Beach Data Science
A day in the life of a Boom Beach data scientist – talk given at Helsinki Data Science meetup
Talk |