Comment by freakynit
7 hours ago
And AlphaGo Zero .. probably the first real-world deployment of a self-improving system that beat humans.
7 hours ago
And AlphaGo Zero .. probably the first real-world deployment of a self-improving system that beat humans.
> probably the first real-world deployment of a self-improving system that beat humans.
Isn't that Checkers right from the dawn of reinforcement learning?
I think that credit might go to IBM:
https://en.wikipedia.org/wiki/TD-Gammon
It was a huge advancement but it did not beat the world champion. AlphaGo is noted for being a self-learning system that became better than all humans. Chess engines had long been there but were not self-learning before AlphaZero.