[Computer-go] algorithm quality assessment

Don Dailey dailey.don at gmail.com
Wed Jun 12 15:08:14 PDT 2013


I don't quite see the point.   The goal is to find the best possible hand
YOU can make with your 13 cards and there is no betting,   so I see no
point in using Monte Carlo here.

What am I missing?

Is it whether to sacrifice one of the 3 hands to strengthen the other 2?
 Or in the case of a really bad hand to at least make 1 really strong hand?


Don


On Wed, Jun 12, 2013 at 6:03 PM, Jason House <jason.james.house at gmail.com>wrote:

> For a particular breakdown into 3 hands, it should be possible to do a
> monte carlo simulation by randomly distribute the remaining cards to the
> other players and then randomly separating each player's cards into 3
> hands. A node in the search tree would be scored as the average result of
> many simulations.
>
> I can think of a few ways to build a search tree. If you have experience
> in the game and know a few general strategies, they will likely be very
> handy for achieving enough strength to evaluate the approach. The search
> tree should be able to give feedback on which strategy is best. The same
> strategies may also help improve the random opponents, but that might
> require more care. It's easy to introduce bias.
>
> Sent from my iPhone
>
> On Jun 12, 2013, at 4:06 PM, Oleg Barmin <j2ee_designer at mail.ru> wrote:
>
> Sure. It's open chinese poker:
> http://www.pokerlistings.com/poker-rules-chinese-poker
>
>
> Среда, 12 июня 2013, 20:57 +01:00 от Nick Wedd <nick at maproom.co.uk>:
>
>   On 12/06/2013 20:33, Oleg Barmin wrote:
> > > For quality assessment, play many games against one or more reference
> > opponents.
> > It's difficult to assament algorithm with a game against humans. The
> > game is young and there are no recognized masters at the moment. So it's
> > very hard to find human-opponent with a really good game skills.
> >
> > > With card games you can get some serious intransitivity, rocks,
> > paper, scissors type of stuff.
> > The aim of this game is to max your scores. Each turn you need to select
> > one of three choices. Each choice has an expectation value of your
> > scores. Optimal strategy here is to select a choice with max expectation
> > value. But it will take a years to calculate an expectation value at the
> > start of the game. So the game has no such intransitivity as rocks,
> > paper, scissors.
> > At the last turns we can make a complete choice enumeration and
> > calculate an exact scores expectation value ( does go algorithms use the
> > same technique? ) . It's not the way for the first half of the game. But
> > the first half is more important.
>
> Can you give a link to the rules of this game? Or even just tell us its
> name?
>
> Nick
>
> >
> > Oleg
> >
> >
> > Среда, 12 июня 2013, 14:24 -04:00 от Don Dailey <dailey.don at gmail.com<https://e.mail.ru/sentmsg?compose&To=dailey.don@gmail.com>
> >:
> >
> >
> >
> > On Wed, Jun 12, 2013 at 11:30 AM, David Fotland
> > <fotland at smart-games.com<https://e.mail.ru/sentmsg?compose&To=fotland@smart%2dgames.com>
> > <sentmsg?mailto=mailto%3afotland at smart%2dgames.com>> wrote:
> >
> > For quality assessment, play many games against one or more
> > reference opponents.
> >
> >
> > Especially for a game that is not a game of perfect information such
> > as go or chess. With card games you can get some serious
> > intransitivity, rocks, paper, scissors type of stuff.
> >
> > Don
> >
> >
> > ____
> >
> > __ __
> >
> > David____
> >
> > __ __
> >
> > *From:*computer-go-bounces at dvandva.org<https://e.mail.ru/sentmsg?compose&To=%2acomputer%2dgo%2dbounces@dvandva.org>
> > <sentmsg?mailto=mailto%3acomputer%2dgo%2dbounces at dvandva.org<https://e.mail.ru/sentmsg?compose&To=sentmsg%3fmailto%3dmailto%253acomputer%252dgo%252dbounces@dvandva.org>
> >
> > [mailto:computer-go-bounces at dvandva.org<https://e.mail.ru/sentmsg?compose&To=computer%2dgo%2dbounces@dvandva.org>
> > <sentmsg?mailto=mailto%3acomputer%2dgo%2dbounces at dvandva.org<https://e.mail.ru/sentmsg?compose&To=sentmsg%3fmailto%3dmailto%253acomputer%252dgo%252dbounces@dvandva.org>
> >]
> > *On Behalf Of *Oleg Barmin
> > *Sent:* Wednesday, June 12, 2013 8:02 AM
> > *To:* computer-go at dvandva.org<https://e.mail.ru/sentmsg?compose&To=computer%2dgo@dvandva.org>
> > <sentmsg?mailto=mailto%3acomputer%2dgo at dvandva.org<https://e.mail.ru/sentmsg?compose&To=sentmsg%3fmailto%3dmailto%253acomputer%252dgo@dvandva.org>
> >
> > *Subject:* [Computer-go] algorithm quality assessment____
> >
> > __ __
> >
> > Hi, everybody,____
> >
> > I am working at the development of a cards game algorithm using
> > MCTS. Technically, the game model is expect minmax tree search,
> > where direct search takes up too much time, that is why I
> > decided to use MCTS.____
> >
> > The issue of using MCST, like any other approximation algorithm
> > is its quality assessment. I am developing an algorithm for a
> > game where no recognized masters exist. How do you think, guys,
> > if for instance Go (or Amazons) provided no way to assess an
> > algorithm playing with professional gamers (or other programs),
> > how would you assets its quality?____
> >
> > My second question: I have not yet learned Go in and out,
> > however in my opinion, any search of a next step should identify
> > a number of options with similar or even the same assessment.
> > How do you resolve this issue?____
> >
> >
> > Best regards,
> > Oleg Barmin.____
> >
> >
> > _______________________________________________
> > Computer-go mailing list
> > Computer-go at dvandva.org<https://e.mail.ru/sentmsg?compose&To=Computer%2dgo@dvandva.org>
> > <sentmsg?mailto=mailto%3aComputer%2dgo at dvandva.org<https://e.mail.ru/sentmsg?compose&To=sentmsg%3fmailto%3dmailto%253aComputer%252dgo@dvandva.org>
> >
> > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
> >
> >
> >
> >
> > Best regards,
> > Oleg Barmin.
> >
> >
> > _______________________________________________
> > Computer-go mailing list
> > Computer-go at dvandva.org<https://e.mail.ru/sentmsg?compose&To=Computer%2dgo@dvandva.org>
> > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
> >
>
>
> --
> Nick Wedd
> nick at maproom.co.uk<https://e.mail.ru/sentmsg?compose&To=nick@maproom.co.uk>
> _______________________________________________
> Computer-go mailing list
> Computer-go at dvandva.org<https://e.mail.ru/sentmsg?compose&To=Computer%2dgo@dvandva.org>
> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>
>
>
> Best regards,
> Oleg Barmin.
>
> _______________________________________________
> 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/20130612/bd58f084/attachment.html>


More information about the Computer-go mailing list