From Tic Tac Toe to AlphaGo: Playing games with AI and machine learning by Roy van Rijn

preview_player
Показать описание
Google's AlphaGo is an extraordinary breakthrough for Artificial Intelligence. The game of 19x19 Go has 1.74×10^172 unique positions and is about a 'googol' times harder to calculate than chess. Experts thought it would take at least another decade before AI would be able to beat the best human players. So how did Google tackle this problem? What algorithms did they use and how do they work?

Рекомендации по теме
Комментарии
Автор

9:42 chess doesn't start with empty board

SB-expx
Автор

19:46 chess hasn't been solved, but i get your point

stephenkamenar
Автор

Weird how clueless the presenter is. Saying chess isn't perfect information game? It's the game that's commonly used as the textbook example of a perfect information game. Also some other weird mistakes here and there.

gJonii
Автор

why is this presenter hell bend to put humans that down. I know alpha go is good but putting human down is not done.

navalarya