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.
AlphaGo Zero: Learning from scratch | DeepMind
-
- Advanced Member
- Повідомлень: 136
- З нами з: 15 липня 2011, 08:20
- Розряд: 1d
AlphaGo Zero: Learning from scratch | DeepMind
- Вкладення
-
- nature24270-s2.zip
- AlphaGo Zero games
- (82.23 Кіб) Завантажено 549 разів
- Dmitriy
- Президент УФГО
- Повідомлень: 1804
- З нами з: 05 квітня 2003, 11:23
- Розряд: 5d
- Звідки: Киев, Украина.
- Dmitriy
- Президент УФГО
- Повідомлень: 1804
- З нами з: 05 квітня 2003, 11:23
- Розряд: 5d
- Звідки: Киев, Украина.
-
- Advanced Member
- Повідомлень: 283
- З нами з: 05 листопада 2006, 16:58
- Розряд: 3k
- Звідки: Польша
Re: AlphaGo Zero: Learning from scratch | DeepMind
Хорошее видео