News for hackers. Stuff that matters.

A comment on Chess-playing neural network LC0 beats Stockfish in 100-game match. Parent comment

Re:Chess-playing neural network LC0 beats Stockfish in 100-g... by mitchellgoffpc on Tuesday May 28, 2019 @07:43PM (#20035558)
Maybe so, but Deepmind isn’t training AlphaZero chess any further! Leela will hopefully just keep on getting better and better :)
[ Parent | on HN ]
Re:Chess-playing neural network LC0 beats Stockfish in 100-g... by mda on Tuesday May 28, 2019 @09:01PM (#20035962)
Eh, If they want, they can train Alpha zero in one day Leela can be trained in 10 years. In any case indeed Leela's progress is impressive.
[ Parent | on HN ]
Re:Chess-playing neural network LC0 beats Stockfish in 100-g... by mot524 on Thursday May 30, 2019 @05:25PM (#20056063)
Training AlphaZero for more than 4 hours on DeepMind's system didn't improve its strength. Makes you wonder if that's as close to ideal chess as we're ever going to get...
[ Parent | on HN ]