mstembera
mstembera
Sometimes the test note is not the same as the github commit message. Being able to search the notes and the name of the test branch using keyword partial match...
@zz4032 This version as described only requires 2 games per opening pair. Also there is no randomness in the TC. @vdbergh @vondele If we could choose any draw rate for...
Thanks for the helpful brainstorming ideas. I think using time odds should help optimize both converting against weaker opponents as well as defending against stronger opponents. Perhaps draw rate isn't...
So the results are: Baseline 10.86 elo +-1.2 Draw rate 81% 3:2 -9.66 elo +-1.2 Draw rate 81% 3:1 -9.71 elo +-1.2 Draw rate 76% I agree it's surprising the...
Ok thanks for catching that! So based on the comments above the tests I ran so far should be invalid. Testing locally could be an option but does anybody know...
I thought the purpose of the approval process was to prevent any malicious code from being executed on the worker machines. It would be irresponsible of us to expose our...
Proper parameter tunes only have changes to numeric constants. Anyone wanting to execute malicious code will obviously not abide by this.
Most exciting to me is the mention of transformer. Can we know more?
Would transformers even be useful for SF?
@vondele Thanks for the link. I wasn't aware. April 1st aside LC0 has switched to transformers so there must be some merit for it at least. Anyone know if there...