Re:Multiplayer AlphaZero
by dmurray on Wednesday October 30, 2019 @05:34AM
(#21395899)
And it's already been done for the chess version, in a community effort[0]. Well, "recomputing the weights" isn't plausible for a neural network of this size, but computing weights that give the network a similar level of performance.
Re:Multiplayer AlphaZero
by narrator on Wednesday October 30, 2019 @08:00AM
(#21396709)
One thing I think that will be critical to the future of software is community efforts to build deep neural nets that match the AI power of the big companies.
[0] https://lczero.org/