There has been quite a bit of work (and several papers) on using CFR for games with >2 players. It is not theoretically guaranteed to converge to a Nash, and usually doesn't in practice either (there's one case in a toy game, in 3p Kuhn poker, where it does converge). However, even though it doesn't converge to Nash, the algorithm is still well defined, and the resulting strategies appear strong in competitions against other computer adversaries, as demonstrated in the Annual Computer Poker Competition.