David J Wu

Right now in particular this affects some of the SGF files from the computer Go server (http://www.yss-aya.com/cgos/), that's where I ran into this issue. Some of these files contain escaped...

FROZEN_SYM_BD is a global defined in the conf/*_pb2.py files that is produced by the hacky protobuf patching system that runs on top of the protobuf compilter that should get run...

Here is where the protobuf message for ParlaiFlags is defined: https://github.com/facebookresearch/diplomacy_cicero/blob/main/conf/agents.proto#L692 In theory if everything is working, this should get compiled by make into various definitions in the autogenerated file...

Yes, KataGo is GPU-training-limited to some extent on my setup, hitting each training sample about 2-4 times, but with 8 symmetries to learn. But this also means it's probably selfplay-limited...

How much faster is it? I would think that it would be many, many years. Even if it's a good GPU, one GPU isn't much. But if you merely want...

Thanks. I guess I don't know what you're doubtful about? Both of the things I've said sound like they're still true. 8x isn't very much to compete with a run...

Anyways, the GPU you mention sounds impressive and would certainly make doing experiments faster and easier. I tend to think of it all on a continuum - saying that it's...

Yes that was my paper. Are you only interested in getting to ELF's strength, or only to the relatively weak strength we reached in the paper? In your initial post,...

By the way, if you're serious about doing hundreds of runs to study the variety of play that results, let me know how I can support you or if you...

> hence my original question. I don't know what your original question is, beyond "how fast could you go from zero to the current ELO?" and I've answered that. But...