I like the topic of aesthetics in gameplay. I think the focus in previous studies in chess was more on compositions (artificial problems) than on actual games, so the question is not whether a player plays beautifully, but whether a problem is elegant and beautiful. And they did come up with interesting measures - certainly problems where bold sacrifices have to be made, weak pieces are used effectively against strong pieces, etc are more interesting than problems that can be solved in expectable and routine ways. "Heuristics are successfully violated" in beautiful problems, as Margulies writes. Would certainly be interesting to define such metrics in Go. Problems where the only good move violates traditional patterns or "good form" or is in some other way surprising and interesting, as opposed to just being hard to find because you have to think through many variations ("neither strangeness nor difficulty produces beauty"). I could imagine measuring the distance between a heuristic evaluation (the output of a DCNN for example) and the result of a deep search, for example. Many computer scientists have problems with concepts that aren't immediately open to formalization, or even require psychological insight, but it's worth it IMHO :)
Cheers, Hendrik _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go