Re:Alpha Go Zero: How and Why It Works
by eru on Sunday November 05, 2017 @09:46AM
(#15629612)
Of course, these techniques you have mentioned were known before and tried. The big thing in AlphaGo Zero is that they found a way to make them work and the resulting architecture even manages to looks simple.
(Eg AlphaGo using two different networks for policy and valuation was a big breakthrough back when it was young, because people couldn't make the single network one work so well.)
For temporal difference learning the article about TD-Gammon, a backgammon AI from the early 90s, is great: http://www.bkgm.com/articles/tesauro/tdl.html (It's linked from the Wikipedia article you referenced, too.)
(Eg AlphaGo using two different networks for policy and valuation was a big breakthrough back when it was young, because people couldn't make the single network one work so well.)
For temporal difference learning the article about TD-Gammon, a backgammon AI from the early 90s, is great: http://www.bkgm.com/articles/tesauro/tdl.html (It's linked from the Wikipedia article you referenced, too.)