Machine learning – How do Chess Engines work?
In his talk at Machine Learning Conference 2019 in Munich, Oliver Zeigermann talked about how chess engines work. Game playing is a classic discipline of AI and had a major break through in the 90s when Deep Blue defeated Kasparov and arguably became the world’s best chess player.
First, Oliver Zeigermann looks at which algorithms made that success possible and how they are still used within Stockfish, one of the leading chess engines. In this part, he also covers Minimax and AlphaBeta pruning.
However, the emphasis of this machine learning talk is on Monte Carlo Tree Search and its advanced use in AlphaZero that relies on zero human heuristics and without even an opening library. You will learn how it trains using self play on a convolutional ResNet architecture. At the end, he briefly looks at a great game between Stockfish and AlphaZero and why the era of classic chess engines might be over.