[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Bug-gnubg] Neural network symmetry question
From: |
Mark Higgins |
Subject: |
Re: [Bug-gnubg] Neural network symmetry question |
Date: |
Sun, 11 Dec 2011 17:22:45 -0500 |
I tried a little experiment on this: a 10-hidden-node network with a single
probability-of-win output, but two setups. The first doesn't have a "whose turn
is it" input and doesn't add any symmetry constraints. The second has the extra
inputs for the turn and makes the symmetry constraint I described.
I trained them in parallel and benchmarked them against pub eval and against
each other.
The symmetric case performed a little better: it trained more quickly, did
better against pub eval, and was on par or a little better than the other case
when playing head to head.
Details and data here:
http://compgammon.blogspot.com/2011/12/testing-value-of-symmetry-constraint.html
Of course not conclusive with such a simple setup, but kind of suggestive
anyways.
On Dec 10, 2011, at 2:22 PM, Mark Higgins wrote:
> Thx! Makes sense. Though I wonder if adding back in the "whose move is it"
> input and reducing the hidden->output weights by half ends up as a net
> benefit for training. Maybe I'll test it out.
>
>
>
> On Dec 10, 2011, at 2:06 PM, Frank Berger <address@hidden> wrote:
>
>> Hi Mark,
>>
>>> If I take a given board and translate the position into the inputs and then
>>> evaluate the network, it gives me a probability of win. If I then flip the
>>> board's perspective (ie white vs black) and do the same, I get another
>>> probability of win. Those two probabilities should sum to 1, since one or
>>> the other player must win (or equivalently, the probability of white
>>> winning = probability of black losing = 1 - probability of black winning).
>>
>>
>> I assume your assumption is wrong. IIRC in an earlier paper there was an
>> input to indicate who's on. It is much simpler to present the position from
>> the point of the moving player, because the net has to learn less. I'm not
>> that familiar with the gnubg code, but I think they do it in this way, so
>> you can't just turn the perspective.
>>
>> ciao
>> Frank
>> _______________________________________________
>> Bug-gnubg mailing list
>> address@hidden
>> https://lists.gnu.org/mailman/listinfo/bug-gnubg
- [Bug-gnubg] Neural network symmetry question, Mark Higgins, 2011/12/09
- [Bug-gnubg] Neural network symmetry question, Frank Berger, 2011/12/10
- Re: [Bug-gnubg] Neural network symmetry question, Mark Higgins, 2011/12/10
- Re: [Bug-gnubg] Neural network symmetry question,
Mark Higgins <=
- Re: [Bug-gnubg] Neural network symmetry question, Joseph Heled, 2011/12/11
- Re: [Bug-gnubg] Neural network symmetry question, Mark Higgins, 2011/12/11
- Re: [Bug-gnubg] Neural network symmetry question, Mark Higgins, 2011/12/12
- Re: [Bug-gnubg] Neural network symmetry question, Øystein Schønning-Johansen, 2011/12/12
- Re: [Bug-gnubg] Neural network symmetry question, Ian Shaw, 2011/12/16
- Re: [Bug-gnubg] Neural network symmetry question, Thomas A. Moulton, 2011/12/16
- Re: [Bug-gnubg] Neural network symmetry question, Ian Shaw, 2011/12/16
- Re: [Bug-gnubg] Neural network symmetry question, Joseph Heled, 2011/12/16