The linked paper is worth reading, and an interesting extension to inductive logic programming (ILP), a symbolic-logic-based approach to generalizing from examples.
The more general idea of learning from watching someone play isn't that new, but it's usually in more restricted contexts. For example, the system may be preprogrammed with the rules of chess, and then learns how to play chess well from logs of expert play. The work here has some pretty clever representations to allow it to start with a general hypothesis of any board-like game and then narrow down the rules of a particular game by observation.
This is actually very old idea. I remember some game creator program on the Apple II that you could teach games. Probably nothing as sophisticated as chess, but maybe tic-tac-toe and connect four. Unfortunately, this was over twenty years ago, so the name is lost to me at the moment. I'll update if I can find it.
Using chess as an example, and not knowing how the program works, I idly wonder if it would pick up such oddities as: en pessant pawn captures, being unable to castle out of check or to castle across check (e.g. White attempts to castle kingside but Black is attacking f1), the fifty-move rule (I expect it would get threefold repetition), and perhaps even the fact that you can promote pawns to pieces other than queens.
Much like how a human learns a game by watching people play. For instance, I learned chess casually by watching people play when I was a kid, and I just now found out about en passant pawn captures. (Thanks!)
The more general idea of learning from watching someone play isn't that new, but it's usually in more restricted contexts. For example, the system may be preprogrammed with the rules of chess, and then learns how to play chess well from logs of expert play. The work here has some pretty clever representations to allow it to start with a general hypothesis of any board-like game and then narrow down the rules of a particular game by observation.