Chess-playing neural network LC0 beats Stockfish in 100-game match

Re:Chess-playing neural network LC0 beats Stockfish in 100-g... by gamegoblin on Wednesday May 29, 2019 @12:25PM (#20042159)

I agree with you in general, but to be perfectly fair, even the Zero-style AIs have a few hyperparameters such as block size and CPUCT value etc that can be tuned to produce engines that play differently. And if Stockfish is the measuring stick by which you gauge progress, you'll tune those values to produce good anti-stockfish nets.

That said, I think the effect here is probably negligible.

[ Parent | on HN ]

Re:Chess-playing neural network LC0 beats Stockfish in 100-g... by mot524 on Thursday May 30, 2019 @05:22PM (#20056037)

Except that LC0 wins decisively against all other engines too. You just hear about the wins vs. Stockfish because Stockfish is the best conventional engine so that's more newsworthy.

[ Parent | on HN ]