Легендарный игровой ИИ, который стал пионером в использовании метода Монте-Карло для игры в Го. Программа объединяет случайные симуляции с интеллектуальным поиском по дереву, что позволило ей достичь уровня профессиональных игроков задолго до нейросетевого бума.
A Monte-Carlo evaluation consists in estimating a position by averaging the outcome of several random continuations. The method can serve as an evaluation function at the leaves of a min-max tree. This paper presents a new framework to combine tree search with Monte-Carlo evaluation, that does not separate between a min-max phase and a Monte-Carlo phase. Instead of backing-up the min-max value close to the root, and the average value at some depth, a more general backup operator is defined that progressively changes from averaging to minmax as the number of simulations grows. This approach provides a finegrained control of the tree growth, at the level of individual simulations, and allows efficient selectivity. The resulting algorithm was implemented in a 9 × 9 Go-playing program, Crazy Stone, that won the 10th KGS computer-Go tournament.