"Math", "Machine Learning"

Fucking DeepMind White Papers

-0.8

4.3

1.4

-2.6

-2.1

-0.8

State of the art: Alpha-beta pruning & MiniMax*

*These techniques only work if you can properly evaluate the board position

5.0

3.2

-1.3

-1.9

-4.8

-3.2

1.2

-0.9

-1.3

3. 😤🍆✊

2. 🔀🧠🕸

1. 🎲🌳🔍

Hidden information, real-time 

No defined rules, sloppy inputs 

Positive-sum games, co-operation, communication

✅ Beat world champions (dec 2018)

✅ Outperformed state-of-the-art algos (mar 2020)

❓ Work started in June, 2020