AlphaGo\'s algorithm uses a combination ofmachine learning and tree search techniques, combined with extensive training, both from human and computer play. It uses Monte Carlo tree search, guided by a \"value network\" and a \"policy network\", both implemented using deep neural network technology.[1][5] A limited amount of game-specific feature detection pre-processing is used to generate the inputs to the neural networks.[5]The system\'s neural networks were initially bootstrapped from human game-play expertise. AlphaGo was initially trained to mimic human play by attempting to match the moves of expert players from recorded historical games, using a database of around 30 million moves.[11] Once it had reached a certain degree of proficiency, it was trained further by being set to play large numbers of games against other instances of itself, usingreinforcement learning to improve its play.[1]
출처 : https://en.m.wikipedia.org/wiki/AlphaGo