That would be very interesting indeed! The ideal way for me would be the existence of a programmatical way (preferably in c/c++) to query GNUBG with a position and a dice roll (and maybe some other settings such as ply depth, cubeless/cubeful evals etc) and get a move output, A standalone library/executable that could do the same would also be of use. Last time I checked the GNUBG code (about 8 years ago), it was very difficult to extract such a function. Perhaps things has changed since then and I should give it another try.
Another way would be for both programs to have some kind of communication protocol in place, but I fear this may be impractical for million of games. Nikos On Thu, Dec 5, 2019 at 8:16 PM Joseph Heled <[email protected]> wrote: > Hi Nikos, > > As far as I can see, there is no public repository of Palamedes code. What > would it take to be able to play Palamedes vs. GNUBG programmatically?? > that is, millions or games/matches. > > Don't you agree it will be very interesting to see what happens, and we > can both learn from the results?? > > Thanks, Joseph > > > >
