Machine-translated by Google. Questions are authored in English.
Top

Discussion

What has learning contributed to game playing programs?

  • A.Evaluation functions and policies learned rather than hand tuned
  • B.The replacement of search by direct pattern recognition
  • C.The elimination of any need at all for a game specific representation
  • D.The ability to play games whose rules are not known

Answer: A

Learned evaluations and move priors have replaced decades of hand tuning, and combined with search they produced superhuman play in chess, shogi and go from self play alone. Search remains essential rather than being replaced, representations are still game specific, and the rules must be known to generate the tree. A component learned rather than written, inside an otherwise classical architecture, is the shape most of the recent advances have taken.

No comment is present. Be the first to comment.
Loading…

Post your comment

Please log in or register to post a comment.