Mastering Go without human input

A place to have an open discussion about Math is More

Moderator: Joseph Malkevitch

Joseph Malkevitch
Posts: 1216
Joined: Tue Aug 28, 2007 2:52 pm
Location: Jamaica, New York
Contact:

Mastering Go without human input

Postby Joseph Malkevitch » Fri Oct 20, 2017 2:11 pm

Dear Colleagues,

Games such as checkers, chess, and Go have a rich computational complexity. But as artificial intelligence has advanced software to play these games has reached the point were the software regular beats good human players. The software to play Go that achieved good results against humans was trained by humans, but now a new algorithm for playing Go that learns from previous play results is available and seemingly very successful.

http://www.nature.com/nature/journal/v5 ... 24270.html

It is unclear to me if looking at how the new algorithm plays will improve human play.

Regards,

Joe
Joseph Malkevitch
Department of Mathematics
York College (CUNY)
Jamaica, New York 11451

email:

malkevitch@york.cuny.edu

web page:

http://york.cuny.edu/~malk

Return to “Math is More: General Discussion”

Who is online

Users browsing this forum: No registered users and 2 guests