Alpha Go Zero: How and Why It Works

Re:Alpha Go Zero: How and Why It Works by _0ffh on Sunday November 05, 2017 @03:51AM (#15628735)

For anyone interested: Learn more on TD and RL in general from Sutton (inventor of TD-lambda) and Barto's book: http://www.incompleteideas.net/sutton/book/the-book.html

Sidenote: It used to be that simply googling "sutton barto book" would bring you to the right place with the first suggested link. Now this stuff is so popular all of a sudden, I needed to consult the link I had set on my own page in order to find it. It's curious how the growth of popularity of an idea will with time obscure it's own roots and primary sources. On the plus side, TIL that Sutton's working on a 2nd edition! =)

[ Parent | on HN ]

Re:Alpha Go Zero: How and Why It Works by dfan on Sunday November 05, 2017 @02:00PM (#15630943)

Here is the latest publicly available draft of the 2nd edition (June 2017, 538 pages): http://incompleteideas.net/sutton/book/bookdraft2017june19.p...

[ Parent | on HN ]

Re:Alpha Go Zero: How and Why It Works by _0ffh on Monday November 06, 2017 @04:24PM (#15639144)

Better to use my link, not the deep one. On mine you can click through to the latest draft (as of writing this, November 5th, 2017)!

[ Parent | on HN ]

Re:Alpha Go Zero: How and Why It Works by je42 on Sunday November 05, 2017 @08:07AM (#15629209)

very good book. but it is also very old. why are they using it only now ???

[ Parent | on HN ]