I wonder if this behavior could be avoided by giving a small incentive to
win by the most points (or most material in chess) similar to to the
technique mentioned by David Wu in KataGo a few days ago. The problem right
now is that the AI has literally no reason to think that winning with more
Hi,
recently, Leela-Chess-Zero has become very strong, playing
on the same level with Stockfish-10. Many of the test players
are puzzled, however, by the "phenomenon" that Lc0 tends to
need many many moves to transform an overwhelming advantage
into a mate.
Just today a new German tester
The human passenger is going to be asleep in the car and hopefully not
awakened by something as trivial as braking.
I recently understood how komi is being dealt with by Leela zero (or at
least by petgo). It's so kludgey and yet is 7d at kgs.
So let's just relax on the small optimizations. The
Yes, partly. For Go, putting some partial weight on score maximization
causes KataGo to continue to play strong moves and try to kill things or
seek profitable trades when it's already winning, subject to still being
fairly safe. Since most of the utility is still on win/loss rather than
score,