Show HN: Play Go Against a Deep Neural Network • Hacker News Board

Re: Show HN: Play Go Against a Deep Neural Network

#31

Post by deepnet » Sat, Nov 14, 2015, 4:42 AM UTC

c-clark wrote: post #7

tasuki wrote: post #3

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…

Since this neural net is trained to respond as a professional would to a given board state - could it be that a 'naive' or less sophisticated level of play would elucidate a matching level of response ?

Concretely, if the player plays worse does the net respond at that level ?

Re: Show HN: Play Go Against a Deep Neural Network

#32

Post by iopq » Fri, Nov 20, 2015, 12:43 PM UTC

thaumaturgy wrote: post #8

It was OK. I'm only about 6k, and I slaughtered it pretty badly (32 for black to -47 for white), but it did a respectable job of playing fuseki and there was an exciting semeai that pretty well decided the game. It filled in some of its own territory to capture a dead group I had in a corner. It's particularly vulnerable to trick moves -- I was able to set up some pretty horrifying ripoffs by throwing a stone in to m…

it doesn't actually do any reading, it just plays moves that appear in pro games

like for example, it will play out the ladder because a pro would play there since the ladder doesn't work so escaping makes sense

however, if it works this loses the game

Re: Show HN: Play Go Against a Deep Neural Network

#33

Post by iopq » Fri, Nov 20, 2015, 12:54 PM UTC

cjbprime wrote: post #21

Interesting! Other people seem to think it plays the opening well, but it didn't seem that way to me. Consider this position: http://chris.printf.net/deepgo.png Every corner shows a joseki, so there's been no non-standard play. But globally, white (the computer) seems to me to have blundered by allowing the combination of the lower-right and top-right joseki and N10. Would be curious to hear if stronger players than…

I'm 3k, but it doesn't seem that white is behind in this game because white has komi and gets to move now