11–20 of 33 posts
The bot was better than me in the sense that he knew exactly the best thing to do in "standard" situations and I don't. In a sense he looks more experienced and studied than me. But he did some stupid moves in some other situations in which he had to think more as a human, I imagine.
There doesn't seem to be a way to pass. How do you end the game? As a very bad Go player, the bot managed to be even worse than me in several key engagements, giving me territory I had no right to capture. It still beat me by a little bit, though (I think -- the game never actually ended!) I wonder if complementing the NN with a more traditional tree search would help it play better tactically. EDIT: Also, your paper…
Thanks for catching that, I fixed the link. The network itself has no capability to pass its turn, which is a consequence of the fact it was only trained to predict player moves, not passes (we thought trying to learn when to pass would be difficult and a complication best avoided). So essentially you have to play until it seems clear to you the position is won or lost. If you played on indefinitely the DCNN would st…
It plays the opening and middle game impressively well - provided one plays reasonable moves. I'm a 4 dan amateur player and it had me beat around move 40. Its strength deteriorates to a complete beginner fairly quickly whenever there's a fight or a nonstandard situation.
That's about what I would expect. The two major weaknesses of "naively" training a Go player in this no-look-ahead purely-supervised way are: 1) The training data only consists of positions that occurred in professional games. This means positions that are not likely to occur in that context have no training data, making the network liable to play poorly. 2) The lack of any kind of planning ahead means situations tha…
Sometimes it says ‘Illegal move: Suicide is not allowed!’ after I play (black), then it passes my white control to me. Is this intended or bug?
Earlier quoted context omitted.
Thanks for catching that, I fixed the link. The network itself has no capability to pass its turn, which is a consequence of the fact it was only trained to predict player moves, not passes (we thought trying to learn when to pass would be difficult and a complication best avoided). So essentially you have to play until it seems clear to you the position is won or lost. If you played on indefinitely the DCNN would st…
But it doesn't seem possible on the web link for the player to pass and then see the score?