Re: [Computer-go] fast + good RNG

40% sounds pretty high. Are you sure its not an artefact of your profiling implementation? I prefer not to instrument, but to sample stack traces. You can do this using gdb by pressing ctrl-c, then type bt. Do this 10 times, and look for the parts of the stack that occur often.  __

Re: [Computer-go] What's a good playout speed?

By the way, for mcts you dont need time controls. Each move takes the same amount of time, since you just do n playouts, and choose n as you like.  I think my playouts took 2s, which was enoufht for 4 playouts i suppose, but it was in novemebr, dont remember clearly... It was obvious that ad

Re: [Computer-go] What's a good playout speed?

Automatch is automatch: the other person doesnt choose to play rhe bot. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] What's a good playout speed?

You can name name a specific opponent, and then your bot will play against it.  Automatch works, but tends to result in lots of people being forced to play your bot, and then leaving the game, after the bot took ages to play in some ridiculous location, which is kind of embarrassing :-P ___

Re: [Computer-go] monte carlo search; all valid moves?

Oh wait, superko check is not that cheap, but it is so rare, you can probably ignore it in playouts, and jist check befote submitting a move to the server. If its superko, then jist pass pethaps. ___ Computer-go mailing list Computer-go@computer-go.org

Re: [Computer-go] monte carlo search; all valid moves?

20 playouts per second is pretty slow. Are you sure youre not just looping around endlessly for 1 moves or something?  Playing in a dead area is legal, as is filling your own eyes etc. Only suicide, and ko is illegal. Even superko is a pretty cheap check. 

Re: [Computer-go] Cogito--another minimal Go engine

I guess one could zip it too. Itd make the code smaller, and no less intelligible :-P ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] [ANN] Michi - 15x15 ~6k KGS in 540 lines of Python code

Oh wow, 640 lines? And gets 6k? Thats impressive! ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] [ANN] Michi - 15x15 ~6k KGS in 540 lines of Python code

Cython works well too. Sage uses cython. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Fwd: Teaching Deep Convolutional Neural Networks to Play Go

> The important thing is that the games don't have to be played perfectly: They >just need to be significantly better than your current model, so you can tweak >the model to learn from them. Thats an important incite. I hadnt thought of that.  Maybe could combine with some concept of "forgettin

Re: [Computer-go] Best resources to get started with UCT?

> Thanks! That's a great data point as it should be easy to run my own bot on > exactly the same hardware Hmmm, you know what. I bet the playouts i just mentioned were 11x11 playouts... 19x19 should be quite a lot slower...  ___ Computer-go mailing li

Re: [Computer-go] Best resources to get started with UCT?

- Petr's masters paper is good - i heard on random kgo chat that: uct + RAVE + 3x3 patterns => gets you a 1dan player Unfortunately, uct + fast playouts wont get you much further than 25-20 kyo, as far as i can tell, in my own experience. (by the way, i was getting 84000 playouts a second on an

Re: [Computer-go] alternative for cgos

> Starting and stopping containers is so fast that I can afford to only start > bots immediately after its opponent plays, request a single move, and > terminate it. Thats interesting. And impressive.  ___ Computer-go mailing list Computer-go@computer

Re: [Computer-go] Testing on different board sizes

My bot loses quite capably on 13x13. But it loses even more on 19x19 :-D  Original message From: Andreas Persson Date:08/01/2015 5:16 PM (GMT+08:00) To: computer-go@computer-go.org Subject: [Computer-go] Testing on different board sizes Hi, I am running some test build

Re: [Computer-go] Move Evaluation in Go Using Deep Convolutional Neural Networks

> as I want to by graphic card for CNN: do I need double precision performance?  Personally, i was thinking of experimenting with ints, bytes, and shorts, even less precise than singles :-)___ Computer-go mailing list Computer-go@computer-go.org http://

Re: [Computer-go] Move Evaluation in Go Using Deep Convolutional Neural Networks

Whilst its technically true that you can use an nn with one hidden layer to learn the same function as a deeper net, you might need a combinatorally large number of nodes :-) "scaling learning algorithms towards ai", by bengio and lecunn, 2007, makes a convincing case along these lines.  _

Re: [Computer-go] Move Evaluation in Go Using Deep Convolutional Neural Networks

Aja wrote: > We haven't measured that but I think "move history" is an important feature > since Go is very much about answering the opponent's last move locally > (that's also why in Go we have the term "tenuki" for not answering the last > move). I guess you could get some measure of the impo