[tiler]

I would guess that they trained AlphaGo from many thousands of hours of match footage. Writing a computer vision script to segment / extract the data may cost cycles as you say, but would save many human hours by eliminating the need to re-watch the footage and literally type out state information for each move.

[ironrabbit]

Alphago was actually trained directly on game state (plus some extra computed state like "how many liberties will I have if I play this move" or "will I win this ladder"). A huge number of pro games (and countless amateur games) are available on servers like KGS in a nice computer-digestible format.

[SamBam]

Again, that doesn't make sense because the moves have almost certainly already been typed out by somebody. It's the same in chess. There are databases containing millions of games.

[komaromy]

I'm not too familiar with Go, but in chess we have millions of text-format games and very little real-time footage.