Completely backwards. There is no obvious score function for Go. That's how AlphaGo broke through, it was able to figure out a scoring method to actually accurately gauge how well it was doing so it could learn and improve.
If what you are saying is true, how does anyone know the game is over? there is a clear win condition. I know that just like with chess, knowing the current vAlue of the board is difficult, but win or loss is clear.
It is often the case that beginning go players don’t know when to quit. The question becomes more subtle as the players increase in skill. It is never as simple as “checkmate” — think more in terms of “mate in three”, except it’s more like “mate in 5-10” in several locations across the board.
