[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Bug-gnubg] Neural network symmetry question
From: |
Joseph Heled |
Subject: |
Re: [Bug-gnubg] Neural network symmetry question |
Date: |
Mon, 12 Dec 2011 11:44:19 +1300 |
My experience tells me that 100,000 trials may not be sufficient.
With today's computing power it should be easy to do at least a
couple of millions.
-Joseph
On 12 December 2011 11:22, Mark Higgins <address@hidden> wrote:
> 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 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, 2011/12/11
- Re: [Bug-gnubg] Neural network symmetry question,
Joseph Heled <=
- 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, Ã˜ystein SchÃ¸nning-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