Ryan Benitez wrote:The program Probe plays Stratego and won the 2007 Computer Stratego Championship but does not beat humans. My hope is to at least beat Probe.
Zillions is the strongest Stratego computer player. Of course, it cheats by knowing all your pieces from the beginning
Back on topic, I would also like to see Fruit released.
As a Zillions author, I can definitely confirm that! Actually, making programs play well in hidden knowledge games is very challenging (well, without cheating, of course) It is also a lot more like real life, where we never quite know where all the pieces are. When I retire, I hope to devote a lot of time to trying to solve this.
Lion wrote:Where can we find this new Fruit engine ?
regards
Nowhere,the author must release it
_No one can hit as hard as life.But it ain’t about how hard you can hit.It’s about how hard you can get hit and keep moving forward.How much you can take and keep moving forward….
Lion wrote:Where can we find this new Fruit engine ?
regards
Nowhere,the author must release it
Would be suprised if Ryan reholds longer than necessary, but clearly, when there's a good chance it significantly streghtened, there's probably good motives to test and search for improvements in an additional period.
However, as Ryan stated some months ago, the goal isn't a no. 1, but and engine that people, us, can fifle with, twisting the parameters. I like that
George Tsavdaris wrote:So when you will release current Fruit 2.3.4n or whatever newer in the public? You've said after CCT10 but you didn't
Ryan Benitez wrote: It may seem silly but my main focus right now is writing a computer Stratego program.
Why silly? Not silly at all.
Do you know of any other such engine that would play Stratego? It seems difficult to write a decent one engine. And to outplay humans seems very difficult also.....
The program Probe plays Stratego and won the 2007 Computer Stratego Championship but does not beat humans. My hope is to at least beat Probe.
What do you mean by "does not beat humans"?
Does it mean not beating the best players or does it mean not beating most of the humans who play the game?
Uri Blass wrote:Does it mean not beating the best players or does it mean not beating most of the humans who play the game?
Uri
It may beat beginner players but it's not good against experienced humans players. Even I was about to beat it in tournament mode on my first try, and I haven't played stratego for several years.
That's to be expected as Stratego is a game of incomplete information and it is still a wide open field for AI research.
Probe is still clearly the best Stratego program (Mainly because it's extremely good at the endgame, compared to other programs.)
George Tsavdaris wrote:So when you will release current Fruit 2.3.4n or whatever newer in the public? You've said after CCT10 but you didn't
Ryan Benitez wrote: It may seem silly but my main focus right now is writing a computer Stratego program.
Why silly? Not silly at all.
Do you know of any other such engine that would play Stratego? It seems difficult to write a decent one engine. And to outplay humans seems very difficult also.....
The program Probe plays Stratego and won the 2007 Computer Stratego Championship but does not beat humans. My hope is to at least beat Probe.
What do you mean by "does not beat humans"?
Does it mean not beating the best players or does it mean not beating most of the humans who play the game?
Uri
I suspect most humans that know the rules can beat it.