Michael Pang
Michael Pang
By training the model with a similar config as in this repo (7 residual blocks of 256 depth) on FICS games, I think it's not doing too bad: (I played...
Could someone write a quick documentation of the input planes? Here's what I think it is: The last 8 board positions. each one 8x8x12 Current state, also 8x8x12 Side to...
Has anyone tried experimenting with the virtual loss parameter? Currently it does n+=3 and w-=3 on entering a node, but intuitively I have no idea what it does except discourage...
Where can we share our weights and training data? I.e. to get a head start with your "good results" Edit: model_best_config.h5 seems to be missing from the ftp server
What's the reasoning behind having the first layer smaller than the middle layers, unlike what the picture shows? Is it to reduce the number of parameters and overfitting, or simply...
Usually when pushing a crafting discipline I use an item booster, but the guide doesn't account for that so I end up with some extra mats at the end. It...
Fix for https://youtrack.jetbrains.com/issue/PY-38835 Not tested
Allow a command line option to specify which files to deploy, or even better take it as standard input so it can be piped with git diff.
For any values of k or n greater than 2 the fastest algorithm is probably to simply use a hash-table which would be amortized O(n). But the answer given suggests...