News for hackers. Stuff that matters.

A comment on Ask HN: Can we adapt AlphaZero's self-play technique for better human learning?. Parent comment

Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by paulcole on Friday December 08, 2017 @06:17PM (#15882959)
> AlphaZero plays games with (1) perfect information

I'm not sure why this matters? Everyone plays chess with perfect information. Both players see the entire board and all possibilities unlike, say, Scrabble or poker.

[ Parent | on HN ]
Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by theptip on Friday December 08, 2017 @06:53PM (#15883174)
I think GP meant that in the sense of "AlphaZero can only play games that have perfect information". It's a restriction of the algorithm, not a statement about how AlphaZero approaches the games it plays.

This is why AlphaGo leveled up into AlphaZero playing Chess, and didn't learn to play Starcraft (yet).

[ Parent | on HN ]
Re:Ask HN: Can we adapt AlphaZero's self-play technique for ... by paulcole on Friday December 08, 2017 @07:10PM (#15883252)
ah yeah, i gotcha. my bad
[ Parent | on HN ]