[Computer-go] useless ko threats

[Álvaro Begué]

I think the solution is the introduction of some flavor of minimax
into the tree search. For instance, once a node has been visited more
than a certain number of times, the score that we'll back out from it
is just the score of the best child, instead of an average that might
be polluted by bad moves.

Of course someone else would have to figure out the details of how to
do this. :)


Álvaro.


On Tue, Mar 6, 2012 at 8:48 AM, Oliver Lewis <ojflewis at yahoo.co.uk> wrote:
> What you're describing sounds like Peter Drake's "Last Good Reply" and its
> many variations, but I'm not sure if that's what you mean by "context
> sensitive RAVE".
>
> Baier, H. and Drake, P. (2010). “The Power of Forgetting: Improving the
> Last-Good-Reply Policy in Monte-Carlo Go”. IEEE Transactions on
> Computational Intelligence and AI in Games 2:4, pp. 303-309.
>
>
>
> On Tue, Mar 6, 2012 at 2:13 PM, Stefan Kaitschick
> <stefan.kaitschick at hamburg.de> wrote:
>>>
>>> Lazarus had that problem too and before that my simple bot had it really
>>> badly because it did not have the benefit of a tree search.     I don't know
>>> if discounting the move is a reasonable solution or not, perhaps it is.
>>> But I think that if you can solve it in the playouts you solve it in
>>> general.     You almost need to determine in the playout how to refute a
>>> stupid ko threat but I don't think that is simple at all.
>>>
>>> Don
>>>
>>
>> Solving it in the playouts would be great, but that puts all the load on
>> move generator.
>> I'm thinking about how to improve the tree, given that the move generator
>> can't be perfect.
>> The damage is also much larger in the tree.
>> Worst of all is the top level of course. :-)
>> But the whole tree could benefit by being littered up less by ko threat
>> permutations.
>>
>> Maybe something like the killer heuristic in chess could help weed out ko
>> threats, by remembering the refutations.
>> Has a context sensitive RAVE been tried?
>> Something like remembering where in the 5 by 5 vicinity the last opponents
>> move was played.
>>
>> Stefan
>>
>>>
>>>
>>>
>>
>> _______________________________________________
>> 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