I understand that using games from humans to learn about life and death introduces all sorts of biases. That's why I tried to use games from an engine instead.
In their standard configuration, MCTS engines will sometimes let lots of groups die after they know the game is hopeless, or if they have a large advantage and they still see a guaranteed victory after the group dies. That's why I tried to configure Pachi to maximize score for this particular purpose. However, as I said, I couldn't get Pachi to really maximize score and play the games to the bitter end; in a good fraction of the games there were dead stones left on the board, and in some games the penultimate eye of a group was plugged for no good reason (probably because of some bug in determining if it's OK to pass). Álvaro. On Fri, Jan 15, 2016 at 4:26 PM, Michael Sué <michael....@gmx.de> wrote: > Hi, > > My experience is the same: My CNN was a very poor judge of life and >> death. Part of the problem is that I couldn't get Pachi to behave >> exactly the way I wanted (play to maximize score; play to the bitter >> end, assuming everything left after two passes is considered alive). But >> perhaps there is some deeper problem, or we are just missing an >> important twist to make the technique work. >> > > I think the problem with live and death is that if it comes to a group > that will die the pro will resign; if he can save the group the bot may not > even got it that there might have been a live and death issue. > > So, why can't you train the DNN on pure live and death problems, just like > human players do it - from time to time. There are many collections (some > even with solutions). > > - Michael. > > > _______________________________________________ > Computer-go mailing list > Computer-go@computer-go.org > http://computer-go.org/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
