Nature-2017-Mastering the game of Go without Human Knowledge (unpublished version by DeepMind company)

This Nature paper presents a deep reinforcement learning (DRL) algorithm without supervision by humans that is more clean and elegant than their previous DRL algorithm (published also in Nature). Cool! Here I upload the unpublished version of this paper as well as supplementary information in order to help someone who want to read it. In the following, I give out the "Abstract" (cited from the Nature paper):

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from selfplay. Here, we introduce an algorithm based solely on reinforcement learning, without human data, guidance, or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

see DeepMind's blog introducing this paper in https://deepmind.com/blog/alphago-zero-learning-scratch/