We will look about reinforcement learning for games and go through some of the techniques that used to build Alpha Go, Google Deepminds AI that recently beat the world’s best human Go player. We will then use those techniques in TensorFlow to build an AI that can master Tic-Tac-Toe.
You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.
You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.You’ll probably enjoy these too.
Video
How to become a Kaggle #1: An introduction to model stacking
Marios Michailidis explains some of the considerations for running StackNet and show how they have used it to win Kaggle competitions and generate value for dunnhumby.