Serhat TUNAR-TDO- In 2017, DeepMind Company being introduced by its founders as “the world leader in artificial intelligence research and its application for positive impact” introduced a single system that taught itself from scratch how to master the games of chess named AlphaZero.
In December 2017, AlphaZero stunned the chess community with defeating the Stockfish, which was the strongest chess engine in the world at that time. And AlphaZero achieved this success only after 4 hours of self-play the game.
But how could AlphaZero defeat the Stockfish with teaching the game itself? The company states in their website that Traditional chess engines – including the world computer chess champion Stockfish - rely on thousands of rules and heuristics handcrafted by strong human players that try to account for every eventuality in a game. AlphaZero takes a totally different approach, replacing these hand-crafted rules with a deep neural network and general purpose algorithms that know nothing about the game beyond the basic rules.
And when the company decided to test their product against the strongest chess engine, AlphaZero defeated the 2016 TCEC (Season 9) world champion Stockfish, winning 155 games and losing just six games out of 1,000.
After achieving a huge success, AlphaZero developers published a paper in Science. And also DeepMind published the games that AlphaZero played with Stockfish in their website. You can find other related documents at there too.
 You can download the open access version of the paper from http://science.sciencemag.org/content/362/6419/1140/tab-pdf