If I understand correctly what it is about, I do have something in my thesis
about that.
p153:" 4.4.3 Mathematical insights: strength VS accuracy", and more
precisely "Theorem 4.4.1 (Accurate simulation player without memory is
strong)"
It is certainly not of direct practical application though.
>
> This seems to be the case and I still do not really on some level
>> understand why. Since with the chinese go rules the board should be
>> effectively stateless (exempting ko information) all the information be
>> contained in the the current position. Why additional information is needed
>> i
I am not entirely sure what you mean here by tuning coefficients do the
heuristics in question require some form of parameterization? How are
these parameters tuned?
There are patterns in the tree and in the Monte-Carlo simulations. Also,
some other expertise (not encoded as pattern) can be us
Thanks for the reply.
2) learned pattern weights are not learnt through
> TD(lambda). RLGO is not
> used in mogo. It was used a long time ago. Hand-designed
> heuristics are
> much more efficient (in particular after heavy
> cluster-based tuning of
> coefficients).
I am not entirely sure what
1) does not hold in mogo anymore, because there's no upper-confidence terms
in MoGo anymore.
I just want to add that this is also true in many codes (either no
upper-confidence term, or with a very small term and no statistical
advantage on the null case).
_
Some MoGo-points-of-views around these 5 points:
Perhaps my understanding of Mogo from the thesis is incorrect. From a
certain standpoint it makes very limited usage of heuristics and seems
to rely solely several published details (in the thesis):
1) UCT+simulation
2) learned pattern weight
I think I being was a bit unclear here. By UCT I meant the combination of
UCT+Simulation. I am just curious why simulation based methods of evaluation
are thus far found to be superior (are they on 19x19?) to traditional bots
which have a different form of evaluation function for a given positio
Quoting Carter Cheng <[EMAIL PROTECTED]>:
Is UCT really that good at finding the best move in alot of situations?
The search algorithms do not find the best move. They prune the bad
ones. The quicker and more reliably bad moves can be pruned the less
candidates remain to be chosen from. T
ke a good hobby- or if I need to "hit the books" so to speak.
Thanks again,
Carter.
--- On Fri, 5/23/08, Jason House <[EMAIL PROTECTED]> wrote:
> From: Jason House <[EMAIL PROTECTED]>
> Subject: Re: [computer-go] batch size and impact on strength
> To: "
On May 23, 2008, at 4:22 PM, Magnus Persson <[EMAIL PROTECTED]>
wrote:
Quoting Carter Cheng <[EMAIL PROTECTED]>:
I remember seeing this in the archive before but I forget the
actual results of the experiment. Does processing simulations in
groups of say 5-10 have any impact on the stren
Quoting Carter Cheng <[EMAIL PROTECTED]>:
I remember seeing this in the archive before but I forget the actual
results of the experiment. Does processing simulations in groups of
say 5-10 have any impact on the strength of the program?
Thanks in advance,
Carter.
Yes, at some point at l
I remember seeing this in the archive before but I forget the actual results of
the experiment. Does processing simulations in groups of say 5-10 have any
impact on the strength of the program?
Thanks in advance,
Carter.
___
computer-go mail
12 matches
Mail list logo
