News for hackers. Stuff that matters.

A comment on Game Theory Reveals the Future of Deep Learning. Parent comment

Re:Game Theory Reveals the Future of Deep Learning by nl on Sunday January 15, 2017 @07:03PM (#13407308)
The entire field of game theory grew out of von Neumann's work on analysis of how people play chess[1].

Quote: What should be noted here is that the format of his intended talks follows exactly the development of game theory up to 1928, beginning with Zermelo on chess, and culminating with von Neumann groping for a theory for three and more players: game theory was still the mathematics of parlor games

[1] http://elaine.ihs.ac.at/~blume/leonardjel.pdf

[ Parent | on HN ]
Re:Game Theory Reveals the Future of Deep Learning by aub3bhat on Sunday January 15, 2017 @07:16PM (#13407379)
Sure but my point is that the Game Theory approach does not helps us in building better Chess playing agents. E.g. how color is used in photography might make a very interesting paper, but from perspective of building an image recognition model its irrelevant.
[ Parent | on HN ]
Re:Game Theory Reveals the Future of Deep Learning by nl on Sunday January 15, 2017 @07:50PM (#13407505)
Yes, I agree.

Although "distance from Nash equilibrium" can be a useful metric to measure the performance of some (game playing) systems.

[ Parent | on HN ]