Re:Alphazero crushes Stockfish in 1,000 game match
by SethTro on Thursday December 06, 2018 @09:03PM
(#18624498)
They are available in the appendix but here's one of them: https://lichess.org/IVW0T4Jd
[ Parent
| on HN ]
Re:Alphazero crushes Stockfish in 1,000 game match
by im3w1l on Friday December 07, 2018 @04:09AM
(#18626141)
Kinda strange stockfish won it since it looked like stockfish pushed for draw via repetition multiple times with alphazero declining.
Re:Alphazero crushes Stockfish in 1,000 game match
by dmurray on Friday December 07, 2018 @06:32AM
(#18626799)
AlphaZero seems to hate repetitions, whether in won drawn or lost positions. I don't understand why, given that it isn't explicitly programmed to have "contempt" like most engines.
Re:Alphazero crushes Stockfish in 1,000 game match
by david-gpu on Friday December 07, 2018 @07:25AM
(#18627069)
Most chess engines have "contempt"? What does it do and what purpose does it serve?
Re:Alphazero crushes Stockfish in 1,000 game match
by detaro on Friday December 07, 2018 @07:43AM
(#18627152)
It influences how the engine values situations that could lead to draws. If playing against an (assumed) weaker opponent, it's likely good to avoid draws when there's probably a good chance to win. In reverse, trying to lock in a draw is better than likely loosing later.
Since repetition is one way to get a draw, an engine with positive contempt (it assumes the opponent to be weaker than itself) will score repetitive moves lower and is more likely to pick something else.