Changes

In the late 70s at [[Carnegie-Mellon University]], [[Hans Berliner]] developed the [[Backgammon]] playing program '''BKG 9.8''' for the [[PDP-10]] to research the principles of [[Evaluation|evaluation]] for another game than chess with a much higher [[Branching Factor|branching factor]] of more than 800 at every node <ref>[[Hans Berliner]] ('''1977'''). ''[http://www.bkgm.com/articles/Berliner/ExperiencesInEvaluationWithBKG/index.html Experiences in Evaluation with BKG, a Program That Plays Backgammon]''. [[Conferences#IJCAI1977|IJCAI, 1977]], hosted by [http://www.bkgm.com/ Backgammon Galore]</ref>. Early versions of BKG played badly even against weak players, but Berliner noticed that its critical mistakes were always at transitions apparently due to [[Evaluation Discontinuity|evaluation discontinuity]]. He applied principles of [https://en.wikipedia.org/wiki/Fuzzy_logic fuzzy logic] to [[Tapered Eval|smooth out]] the transition between phases, and by July 1979, BKG 9.8 was strong enough to play against the ruling world champion [https://en.wikipedia.org/wiki/Luigi_Villa Luigi Villa]. It won the match 7–1, becoming the first computer program to defeat a world champion in any game. Berliner states that the victory was largely a matter of luck, as the computer received more favorable dice rolls <ref>[https://en.wikipedia.org/wiki/Hans_Berliner Hans Berliner from Wikipedia]</ref> <ref>[[Hans Berliner]] ('''1980'''). ''[http://www.bkgm.com/articles/Berliner/BackgammonProgramBeatsWorldChamp/ Backgammon Computer Program Beats World Champion]''. [https://en.wikipedia.org/wiki/Artificial_Intelligence_%28journal%29 Artificial Intelligence], Vol. 14</ref>.

* [[Wee -Chong Oon]], [httphttps://www.informatikdblp.uni-trier.de/~ley/db/indicespers/a-treehd/h/Henz:Martin.html Martin Henz] ('''2007'''). ''[http://www.aaai.org/Library/AAAI/2007/aaai07-098.php M2ICAL Analyses HC-Gammon]''. [http://www.informatik.uni[Conferences#AAAI-trier.de/~ley/db/conf/aaai/aaai2007.html#OonH07 2007|AAAI 2007]] <ref>[http://satirist.org/learn-game/systems/gammon/hc-gammon.html The hillclimbing HC-Gammon] from [http://satirist.org/learn-game/ Machine Learning in Games] by [[Jay Scott]]</ref>