[Computer-go] MCTS + Neural Networks?

Petri Pitkanen petri.t.pitkanen at gmail.com
Wed May 1 22:12:22 PDT 2013


I would say you would loose too many simulations. Besides by using whatever
power to increase simulations/second probably gives better results.
Optimizing simulations is a dark art. I think there are several test to
show thath if you make the simulation AI better the it may make your bot
weaker, even with similar amount sims/move.

Perhaps applying neural nets in tree search part  to bias the search? Like
Many Faces does with opening book.

Petri


2013/5/2 Steven Clark <steven.p.clark at gmail.com>

> Thanks for the link! Looks like a good paper -- I will read it more
> carefully shortly.
> Ignoring computational speed for a moment, is it a reasonable assumption
> that an algorithm that plays a NN-proposed tactical move 50% of the time,
> and a random move 50% of the time, should outperform an algorithm that
> plays a random move 100% of the time?
> So it's just a case of how many playouts do we lose by employing the NN
> (GPUs to the rescue?). For reference, I was using 25 input nodes, 25 output
> nodes, ~50 hidden nodes.
> I guess ultimately it comes down to "make a bot and prove it" :)
>
> -Steven
>
>
>
> On Wed, May 1, 2013 at 9:50 PM, George Dahl <gdahl at cs.toronto.edu> wrote:
>
>> I don't know if neural nets that predict moves have been helpful in any
>> strong bots, but predicting expert moves with neural nets is certainly old
>> news. See http://www.cs.utoronto.ca/~ilya/pubs/2008/go_paper.pdf
>>
>> There might be a place for artificial neural nets in a strong Go playing
>> program, but it is an open question on how to incorporate neural nets well.
>> Software like neurgo used a lot of expert features along with a neural net
>> for global position evaluation and I tried (with very little success) to
>> predict ownership of points on the board using a neural net.
>>
>> It is very hard to get neural nets to help a standard MCTS bot a lot
>> because the neural net needs to be good at whatever it is supposed to be
>> doing and still probably very fast to be useful.
>>
>> - George
>>
>>
>> On Wed, May 1, 2013 at 9:42 PM, Steven Clark <steven.p.clark at gmail.com>wrote:
>>
>>> Hello all-
>>>
>>> Has anyone successfully used neural nets to help guide MC playouts?
>>>  Has anyone used NN to learn patterns larger than 3x3?
>>>
>>> I'm working on a grad-school project, and discovered a few interesting
>>> things.
>>> After analyzing 10,000+ high-dan games from KGS, I find that more than
>>> 50% of the time, moves are played within a 5x5 window centered at the
>>> opponent's previous move (call this a "tactical" move, vs a strategic move).
>>>
>>> I used the FANN library to learn these 5x5 patterns, and found that the
>>> NN could predict tactical moves with ~27% accuracy (and with a >50% chance
>>> that the answer would be in the top 3 moves proposed by the NN).
>>>
>>> Is this old news? Are neural nets just too slow to be helpful to MC
>>> (reduce the playout rate too much?)
>>>
>>> Thoughts welcome. I will be up late finishing the report since it is due
>>> tomorrow ;)
>>>
>>> -Steven
>>>
>>> _______________________________________________
>>> Computer-go mailing list
>>> Computer-go at dvandva.org
>>> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>>>
>>
>>
>> _______________________________________________
>> Computer-go mailing list
>> Computer-go at dvandva.org
>> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>>
>
>
> _______________________________________________
> Computer-go mailing list
> Computer-go at dvandva.org
> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20130502/d2c170c8/attachment.html>


More information about the Computer-go mailing list