[computer-go] Congratulations to LeelaBot2 and to CzechBot

Nick Wedd nick at maproom.co.uk
Thu May 8 15:08:42 PDT 2008


In message <6054b7b40805081347h8f1e739o1dd9ce237f628b51 at mail.gmail.com>, 
Jason House <jason.james.house at gmail.com> writes
>You have a typo "deasd" should be "dead".

Thank you, fixed.

>My personal preferences would be to see the final section change its
>title from "Probation" to "Losses in Cleanup" or some other title
>addressing undesirable issue uncovered in this past tournament.

I have renamed this section to "Losses after Game Stop".  Is this 
reasonable?

>I'd also appreciate it if the old versions of the report can be removed
>completely.  The last thing I want is for a potential employer to
>google me and find one of those pages.

Ok, understood, I have removed them.  I too am glad to see them removed, 
as they reflect badly on me.

Nick

>  They're very easy to
>misinterpret, especially given that my uniform-playout MC bot's
>performance was on par for 19x19 with relatively short time limits. 
>Once upon a time, people thought MC bots would not scale to 19x19. 
>Local biases in playouts, move ordering, and possibly progressive
>widening have changed all that.  I hope to do that one day, but I don't
>yet.
>
>PS: You'll be happy to hear that I've been discussing alternate
>resignation strategies with people.  The lack of resignation in this
>past tournament occurred because time it was a large board with short
>time limits (and my bot is slow).  Everyone I've talked to seems to
>think the threshold I have for resigning are reasonable.  What I have
>right now considers a single move in isolation, but it should be
>possible to consider a sequence of moves together.  Essentially, it'll
>increase the available data to use in the resignation decision and
>avoid incorrect resignations at idiotic points.
>
>
>On Thu, May 8, 2008 at 4:21 AM, Nick Wedd <nick at maproom.co.uk> wrote:
>  In message <482246BC.4080208 at gmail.com>, Michael Williams <
>  michaelwilliams75 at gmail.com> writes
>
>
>>    I agree with Evan 100%.
>
>>    I probably would have gone berserk if I were Jason.  Instead he
>>    handled it with relative grace, considering what was in that
>>    report.
>
>
>  Ok.  I am persuaded that I have acted wrongly here.  I withdraw the
>  probation on Jason's bot, and offer my apologies to him.  I shall
>  rewrite my report (and archive the old one, for the historic
>  record).
>
>  Nick
>
>
>
>>    Evan Daniel wrote:
>
>>>      On Wed, May 7, 2008 at 11:45 AM, Nick Wedd <nick at maproom.co.uk
>>>      > wrote:
>
>>>>        In message <
>>>>        6054b7b40805070659u543a69afvf8b9dffbe75a743e at mail.gmail.com
>>>>        >,
>>>>        Jason House <jason.james.house at gmail.com> writes
>
>
>
>>>>>          Correction: HBotSVN was not reconfigured for speed in
>>>>>          round 3.  It was
>>>>>          set to use two search threads in round 4, and was
>>>>>          compiled in debug
>>>>>          mode for the whole tournament.  I apologize for the
>>>>>          confusing PM's
>>>>>          during the tournament about this.
>
>
>>>>         Thank you for explaining this, I have changed the report
>>>>        accordingly.
>
>
>
>
>>>>>           What is "HBotSVN's technique"?
>
>
>>>>         Its technique is to refuse to admit that its dead groups
>>>>        are dead, and then
>>>>        to waste time in the resolution phase playing meaningless
>>>>        stones. This
>>>>        sometimes gives it a win on time, and is the only way that
>>>>        it wins games.
>>>>        This is annoying for the other competitors.  I know it is
>>>>        not your intention
>>>>        that it behaves like this, but it is in your power to
>>>>        prevent it.  It is not
>>>>        in my power to do anything about it, except by reassigning
>>>>        the results of
>>>>        games which it wins like this:  this is the purpose of the
>>>>        probation.  It is
>>>>        in Bill Shubert's power to change the way the server works
>>>>        so that if only
>>>>        one player sends a final_status_list, it will accept what
>>>>        that player says.
>>>>        I shall suggest it to him.
>
>
>
>
>>>>>          The game end protocol says "To play
>>>>>          in a tournament, programs must either implement both
>>>>>          "kgs-genmove_cleanup" and "final_status_list dead", or
>>>>>          they must play
>>>>>          until all of their opponent's dead stones are removed
>>>>>          from the board.
>>>>>          It's OK if "play until dead stones removed" is an
>>>>>          option, but they have
>>>>>          to make sure that this option is turned on whenever they
>>>>>          are going to
>>>>>          be in a tournament, or they will do poorly in the
>>>>>          tournament!".
>>>>>          HouseBot (HBotSVN) handles this by playing until all of
>>>>>          its opponent's
>>>>>          dead stones are removed.
>>>>>           "final_status_list dead" is not supported.  It's kgsGtp
>>>>>          (not
>>>>>          HouseBot!) that insisists that all stones are alive.  It
>>>>>          annoys me
>>>>>          every time I see the description that it's the bot
>>>>>          that's behaving
>>>>>          badly when it's really a problem with how the
>>>>>          combination of kgsGtp and
>>>>>          the KGS server represent this stuff.
>
>
>>>>         I have changed the wording of my report from "claimed they
>>>>        were alive" to
>>>>        "failed to admit that they were dead".  I have done so
>>>>        because you have
>>>>        persuaded me that it is correct and what I said before was
>>>>        wrong. I do not
>>>>        expect you to be appeased by this.
>
>
>
>
>>>>>          I consider it a bug in kgs that
>>>>>          this perpetually gets misinterpreted by spectators.
>>>>>           Please stop saying that my bot insists all of its
>>>>>          stones are alive.
>>>>>          This could be simplified by either fixing the game end
>>>>>          protocol rules,
>>>>>          or getting kgs fixed (kgsGtp and/or the server).
>
>>>>>           In the round two game, it was HBotSVN that had 3
>>>>>          seconds left on the
>>>>>          clock.  Its opponent, MonteGNU, had almost a minute left
>>>>>          (51 seconds).
>
>
>>>>         Thank you for pointing this out.  I have corrected my
>>>>        mistake.
>
>
>
>
>>>>>          The only games where HBotSVN's opponent got down to very
>>>>>          little time
>>>>>          left was the game against Leela.
>>>>>           The whole probation thing has really pissed me off.  
>>>>>          Maybe one
>>>>>          component of that is first finding out about it by
>>>>>          reading it in the
>>>>>          report.  I have not been implementing "difficult things"
>>>>>          for quite a
>>>>>          while.  Because stuff wasn't working, I suspended all
>>>>>          forward progress
>>>>>          on my bot two months ago.  Since then, I've been
>>>>>          building test
>>>>>          harnesses, writing unit tests, and eliminating bugs.
>>>>>           Did you know that weakbot50k and idiotbot don't
>>>>>          actually handle the
>>>>>          game end at all?  Once both players pass, they switch to
>>>>>          using gnu go.
>
>
>>>>         I didn't know that, but it seems a sensible, robust,
>>>>        solution.
>
>>>>         Nick
>
>
>
>
>
>>>>>           I will no longer participate in these tournaments for
>>>>>          the foreseeable
>>>>>          future.
>
>>>       I fail to see the problem with HBotSVN's behavior.  It is
>>>      playing
>>>      according to the protocol as specified.  Humans judging intent
>>>      and
>>>      reasonableness belong in human tournaments, and possibly
>>>      human-computer tournaments, but most emphatically not in
>>>      computer-computer tournaments.  What would you do if HBotSVN
>>>      implemented final_status_list dead and always returned the
>>>      empty set?
>>>      What if it only returned stones that were unsalvageable even
>>>      in the
>>>      face of opponent passes?  HBotSVN seems to be requiring its
>>>      opponents
>>>      to demonstrate that they are actually capable of killing the
>>>      groups
>>>      they claim are dead.  Given the skill level of some programs,
>>>      and that
>>>      programs are not offendable, this behavior seems at worst
>>>      mildly rude,
>>>      possibly deserving of derision and disrespect, and completely
>>>      undeserving of any sort of sanction.
>>>       It is entirely within the power of the other bots to not lose
>>>      on time.
>>>       If they cannot manage their time, that should be viewed as a
>>>      defect
>>>      no different from not being able to manage sente.  If you
>>>      dislike the
>>>      effect this has on time management, add a single 1-3s byo yomi
>>>      period
>>>      (or some other time system; I dislike Japanese byo yomi but it
>>>      works
>>>      well enough here and is traditional).  Any program that cannot
>>>      play
>>>      out the dispute resolution accurately in 1s byo-yomi had no
>>>      business
>>>      being so confident in its assessment that it should run out
>>>      all its
>>>      time before passing.
>>>       Attitudes like this make me think that these games are to be
>>>      taken
>>>      solely as exhibition games, and not as actual tournaments.  I
>>>      find
>>>      this disappointing, as I think KGS could be a good complement
>>>      to CGOS
>>>      as a forum for computer Go.
>>>       Someday I hope to return to writing a computer Go program.  
>>>      However, I
>>>      can't see myself entering it in any tournament that does not
>>>      precisely
>>>      and accurately specify the required behavior.
>>>       Evan Daniel
>>>      _______________________________________________
>>>      computer-go mailing list
>>>      computer-go at computer-go.org
>>>      http://www.computer-go.org/mailman/listinfo/computer-go/
>
>
>
>>    _______________________________________________
>>    computer-go mailing list
>>    computer-go at computer-go.org
>>    http://www.computer-go.org/mailman/listinfo/computer-go/
>
>
>  --
>  Nick Wedd    nick at maproom.co.uk
>  _______________________________________________
>  computer-go mailing list
>  computer-go at computer-go.org
>  http://www.computer-go.org/mailman/listinfo/computer-go/
>_______________________________________________
>computer-go mailing list
>computer-go at computer-go.org
>http://www.computer-go.org/mailman/listinfo/computer-go/

-- 
Nick Wedd    nick at maproom.co.uk


More information about the computer-go mailing list