Re:Ask HN: Can we adapt AlphaZero's self-play technique for ...
by blktiger on Friday December 08, 2017 @05:09PM
(#15882517)
I have two thoughts:
AlphaZero plays millions of games against itself with a low per-game ROI in much less time than it takes a human playing against an expert with a high ROI. In this way AlphaZero has more work to do than the human to achieve a certain skill level, after which it is probably doing a similar amount of work to the human to continue to improve but can do it in much larger numbers.
On the other hand, I think I've heard of experts at chess playing games against themselves but I can't seem to find a reference at the moment.
AlphaZero plays millions of games against itself with a low per-game ROI in much less time than it takes a human playing against an expert with a high ROI. In this way AlphaZero has more work to do than the human to achieve a certain skill level, after which it is probably doing a similar amount of work to the human to continue to improve but can do it in much larger numbers.
On the other hand, I think I've heard of experts at chess playing games against themselves but I can't seem to find a reference at the moment.