HN Books @HNBooksMonth

Yes I read the book decades ago and it was indeed excellent. IIRC, the technical details are probably too light for the HN crowd, but it was the biographical stories that had interested me.

For an even shorter, and lighter, read on checkers engine, I recommend Blondie24[0].

[0] https://www.amazon.com/dp/1558607838

⬐ fffrrrr

This is really a riveting book. You don't need any interest in checks or computer science to enjoy it.

This is a fun book (published in 2001) about how a professor and his graduate assistant developed a world-class checkers-playing algorithm using neuroevolution:

https://en.wikipedia.org/wiki/Blondie24

https://www.amazon.com/Blondie24-Playing-Kaufmann-Artificial...

(Edit) One of the funniest parts I remember is that they had to leave it running on a Pentium III for like a month or something.

The Blondie24 book was published in 2002.

https://www.amazon.com/product-reviews/1558607838

People need to recognize that this is not a new idea. It may have been groundbreaking in the early 2000s, but Genetic Algorithms + Neural Nets are a relatively old strategy at this point.

Definitely read the book if you want a bit of a throwback. When cutting-edge AI research was about beating players on Yahoo-games Checkers with new techniques.

There's also Blondie24[0], which's got a pretty humorous backstory to its namesake.

[0] https://www.amazon.com/dp/1558607838/

⬐ mholmes680

can second this recommendation. good, quick reading.

This has been the norm since computers could play board games. I read Blondie24[0] about a year back about 2 guys who build a complicated neural network for a checkers program which teaches itself to play by playing against itself and is eventually entered into 'Human' tournaments. It's a really fast read even if you have no experience in AI.

There is also Deep Blue[1], which is famous for once defeating Garry Kasparov in a high profile match.

[0] http://www.amazon.com/Blondie24-Playing-Kaufmann-Artificial-... [1] http://en.wikipedia.org/wiki/Deep_Blue_%28chess_computer%29

⬐ DanBC2

Deep Blue was one computer against one human.

The comment you're replying to is suggesting teams with two members: Computer A and Human A VS Computer B and Human B.

Thanks for the link to the Blondie24 book!

The book Blondie24 is an interesting popular science style account of this type of AI.

http://www.amazon.com/Blondie24-Playing-Kaufmann-Artificial-...

They partially trained their checkers algorithm by playing it online against humans. The funny part was that they couldn't get many opponents until they changed their handle to Blondie24, then game requests came flooding in...