I know that MCTS winrate does not give any usufull information about quality of the move except winning chance
I said that normalized winrates with random komi window give much more information.
So to show the concept I played two games on 13x13 between 1) standard pachi2) and modified pachi with random komi from fixed window [-17.5,32.5] for all game board.c 1404 > return (32.5 - rand() % 51) + board->handicap + scores[S_WHITE] - scores[S_BLACK]; meaning that for EACH quick count I aplliyed komi as a random number from window
Games were close and very informative.First one standard pachi won for 0.5 and lost all points in yose. They played until end.
Second was misread semeai and nakade so while modified was winnig itplayed correct moves and when it lost semeai played nice endgame and lost for 3.5
Please take a look at the games. Leon Matoh
regression--0.sgf
Description: application/go-sgf
regression--1.sgf
Description: application/go-sgf
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
