AlphaGo Zero: Learning from scratch | DeepMind

Geser
Advanced Member
Сообщения: 107
Зарегистрирован: 15 июл 2011, 08:20
Разряд: 1d

AlphaGo Zero: Learning from scratch | DeepMind

Сообщение Geser » 19 окт 2017, 04:35

https://deepmind.com/blog/alphago-zero- ... g-scratch/





The paper introduces AlphaGo Zero, the latest evolution of AlphaGo, the first computer program to defeat a world champion at the ancient Chinese game of Go. Zero is even more powerful and is arguably the strongest Go player in history.

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0.

Изображение
У вас нет необходимых прав для просмотра вложений в этом сообщении.

Аватара пользователя
Dmitriy
Президент УФГО
Сообщения: 1063
Зарегистрирован: 05 апр 2003, 11:23
Разряд: 5d
Откуда: Киев, Украина.

Re: AlphaGo Zero: Learning from scratch | DeepMind

Сообщение Dmitriy » 20 окт 2017, 15:55