Thanks for the tutorial! I have some questions about training
a) Do you use Dirichlet noise during training, if so is it limited to first
30 or so plies ( which is the opening phase of chess) ?
The alphazero paper is not clear about it.
b) Do you need to shuffle batches if you are doing one
What exactly is the innovation that is patented ?
Using short look-ahead searches for tuning evaluation functions ( in this
case a neural network ) is not exactly new.
On Thu, Dec 6, 2018 at 3:28 PM Rémi Coulom wrote:
> Hi,
>
> The new alphazero paper of DeepMind about chess and shogi has been
