Greetings, everyone.

My research group is exploring coevolution as game tree search,  
specifically for the game of Go. We are aware of many attempt to use  
genetic algorithms to evolve players or board evaluators over the  
course of many games, but we are trying to use coevolution to find  
the best move (or at least a good move) during the course of a single  
game. The individuals being evolved are partial strategies, i.e.,  
subsets of the game tree starting at the root but not extending to  
the leaves. When we have two individuals play against each other as  
part of fitness testing, we use the individuals to determine moves  
until we fall of the bottoms of the trees, then finish the game  
randomly, as a Monte-Carlo playout. We've had some preliminary  
success, and will be presenting a paper at GEM'08 next month.

My question: is anyone aware of other work in this area? We haven't  
been able to find any.

Thanks in advance,

Peter Drake
http://www.lclark.edu/~drake/