On 10/23/2017 11:29 AM, Dave Dyer wrote:
I wonder how alphago-0 treats the menagerie of special positions, such as
bent 4 in the corner, thousand year ko, rotating ko, etc.
they are using chinese rules, so bent four just gets played out. have no
idea about strange ko's. there was a double
Zero's MCTS code knows "legal" moves (as a part of rules)
embed (page 22). Bent four will be solved in practice as
she uses Chinese rules.
Hideki
Dave Dyer: <20171023210343.e65bc31a...@eugeneweb.com>:
>
>I wonder how alphago-0 treats the menagerie of special positions, such as
>bent 4 in the
On 2017-10-23 at 19:15, Xavier Combelle wrote:
> Hi Robert Jasiek,
>
> you might have a delusional way to see the game of go and life,
this is quite an insult, IMO, and I’d prefer not to read such personal attacks
in this list. What about staying on-topic?
> but
It will be interesting to realize that those specialized positions
(thousand-year-ko, bent 4) are actually a microscopic issue in game-winning.
s.
On Mon, Oct 23, 2017 at 2:10 PM, uurtamo . wrote:
> We can all "wonder" such things unless we are not too busy to build some
>
We can all "wonder" such things unless we are not too busy to build some
code to filter out such positions and see what actually happened in the
self-play games opened up to everyone to see.
s.
On Mon, Oct 23, 2017 at 11:29 AM, Dave Dyer wrote:
>
> I wonder how alphago-0
I wonder how alphago-0 treats the menagerie of special positions, such as
bent 4 in the corner, thousand year ko, rotating ko, etc.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
I wonder how alphago-0 treats the menagerie of special positions, such as
bent 4 in the corner, thousand year ko, rotating ko, etc.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
If you wanted to do research on a specific joseki to see if AG0 found
weaknesses or explored alternatives, especially in games past day 3 (when
it began besting AGM), it would be quite interesting to see, through that
explicit filter, what kinds of things emerged around that specific joseki.
You
Hi Robert Jasiek,
you might have a delusional way to see the game of go and life, but I
would love that you would not pollute
my mailbox with such a delusional vision. I'm certain that a lot of
person of this mailing list and other forums share my view.
To sum up, I would be pleased and I'm
Deepmind's paper on Alphago Zero (AGZ) gave an unexpected and beautiful answer
to the question I confusedly posted here a while ago:
http://computer-go.org/pipermail/computer-go/2017-January/009828.html
http://computer-go.org/pipermail/computer-go/2017-February/009894.html
==> MCTS is
If the AG got better by playing against itself rather than training on
previous good players then I do not thing training data is that important.
Perhaps it is but google has shown that actually u dont need it. Just loads
of processing will do the trick.
2017-10-23 15:05 GMT+03:00 Jim
On 23.10.2017 14:05, Jim O'Flaherty wrote:
Couldn't they be useful as part of a set of training data for newly trained
engines and networks?
All the millions of games would be very useful for many purposes. E.g.,
I want to know whether the reconstructed knowledge includes such basic
things
No, they are too few games for that.
On Mon, Oct 23, 2017 at 8:05 AM, Jim O'Flaherty
wrote:
> Couldn't they be useful as part of a set of training data for newly
> trained engines and networks?
>
> On Oct 23, 2017 2:34 AM, "Petri Pitkanen"
Couldn't they be useful as part of a set of training data for newly trained
engines and networks?
On Oct 23, 2017 2:34 AM, "Petri Pitkanen"
wrote:
> They are free to use in any attribution. Game score is a reflection of
> historical fact and hence not copyrightable.
from https://twitter.com/Miles_Brundage
https://arxiv.org/abs/1710.07535
https://arxiv.org/abs/1709.01041
On Mon, Oct 23, 2017 at 10:39 AM, Darren Cook wrote:
> > The source of AlphaGo Zero is really of zero interest (pun intended).
>
> The source code is the first-hand
"Petri Pitkanen" wrot:
> They are free to use in any attribution. Game score is a reflection of
> historical fact and hence not copyrightable.
"reflection of historical fact" concerns games that were played
in public. Over the decades, there were several
They are free to use in any attribution. Game score is a reflection of
historical fact and hence not copyrightable. Dunno what use them are to
anyone though.
Petri
2017-10-23 2:29 GMT+03:00 Lucas Baker :
> Hi Robert,
>
> The AlphaGo Zero games are free to use with proper
17 matches
Mail list logo