From 328c8d1e3094a942d6a2edd933c9cc4ab09daab1 Mon Sep 17 00:00:00 2001 From: tslil clingman Date: Sun, 31 Jan 2021 23:33:39 -0500 Subject: Just some #weightgoals ;) It turns out that while i was training on a 0/1 classification problem, i was using 2*eval - 1. Training using this function instead, and on bot-dominated game choices (chosen_player in extract.sh) seems to have given a better evaluation function. At the least, Morten's swindle doesn't work anymore. --- src/pptdb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/pptdb.c') diff --git a/src/pptdb.c b/src/pptdb.c index ecf5caa..557b894 100644 --- a/src/pptdb.c +++ b/src/pptdb.c @@ -198,7 +198,7 @@ int main(int argc, char **argv) { reset_state(size); // Store the outcome of this game. Black win = 1 if (line[read-4] == '0') outcome_black = 1; - else outcome_black = 0; + else outcome_black = -1; // Parse the line r = parse_line(line,read-4); // Adjust counts if we're not generating training data -- cgit v1.2.3