David J Wu

Anyways, if you're interested, go for it! GPU strength is very likely non-blocking for bot-playing-style research, it's more a very-nice-to-have rather than something critical. Even if you lose a factor...

Maybe. If you could find a way to reliably categorize the styles of different players across tens of thousands of games, then you could add some parameters to the human...

As noted in the release notes (https://github.com/lightvector/KataGo/releases/tag/v1.15.0), on linux the versioning of libzip and other libraries makes compatibility very tricky when trying to release raw executables. I recommend you compile...

Have you tried building from source? It's not that hard on linux, and it means that you get to compile katago using exactly all the versions of libraries on your...

Thanks for the discussion. I'll investigate a little and consider what can be done about this. I don't think it's harmful to the training, but having a lot of repetition...

I reviewed probably around 50 different 19x19 training games and I haven't yet seen this opening pattern even one time. You've found some instances of this pattern in training games,...

Thanks for the estimate. If it's perhaps only 0.2% of the total games (including all game types), what is the concern? Are we worried about some kind of overfitting? It...

I don't see any error message in the output. What was the problem?

Some other thoughts: Is the problem that it fail with no error message? Have you tried earlier versions again and do they also have the same problem? What happens if...

Ooooh, I think it might be the case that some of the architecture refactors and renames affected the ability to load a plan cache from before those changes. I will...