AlphaGo - Mastering the game of Go with deep neural networks and tree search
This post is from Deepmind and OpenAI papers series, which I try to summarize and take some notes from some interesting papers from Deepmind and OpenAI. Here I will start with AlphaGo, which tries to combine the Monte Carlo Tree Search algorithm with deep learning to play Go.
That’s it for the first one. In the next post, I will review the AlphaGo Zero paper.