Department of Computer Science and Technology

Technical reports

Exploratory learning in the game of GO

Barney Pell

18 pages


This paper considers the importance of exploration to game-playing programs which learn by playing against opponents. The central question is whether a learning program should play the move which offers the best chance of winning the present game, or if it should play the move which has the best chance of providing useful information for future games. An approach to addressing this question is developed using probability theory, and then implemented in two different learning methods. Initial experiments in the game of Go suggest that a program which takes exploration into account can learn better against a knowledgeable opponent than a program which does not.

Full text

PS (0.0 MB)

BibTeX record

  author =	 {Pell, Barney},
  title = 	 {{Exploratory learning in the game of GO}},
  url = 	 {},
  institution =  {University of Cambridge, Computer Laboratory},
  number = 	 {UCAM-CL-TR-275}