Closed jonthysell closed 6 years ago
Basically, take the static evaluation of the board after one move, and compare it with the deep search result, and tune the weights to make them match.
See https://chessprogramming.wikispaces.com/Reinforcement%20Learning, https://chessprogramming.wikispaces.com/Meep#RootStrap
http://papers.nips.cc/paper/3722-bootstrapping-from-game-tree-search.pdf
Basically, take the static evaluation of the board after one move, and compare it with the deep search result, and tune the weights to make them match.
See https://chessprogramming.wikispaces.com/Reinforcement%20Learning, https://chessprogramming.wikispaces.com/Meep#RootStrap