This has been tried for chess with very limited success. Quinlin, a PhD student of Donald Michie in England, now I believe a professor in Sydney Australia developed the ID3 algorithm and tested it on learning chess.
======================================== On Sat, 11 Jan 2003 22:34:01 -0500 "Ben Goertzel" <[EMAIL PROTECTED]> writes: > > My personal litmus test is whether an AGI can learn and play > high-level > > chess, go, bridge, or other similar games without being coded > specifically > > for these games. The advantage of this test is that it requires > > no physical > > instantiation, and the results are easily quantifiable. > > > > Kevin Copple > > > Hmmm... > > I can imagine an AI system that could achieve this goal without > having > really robust general intelligence.. > > A system that was coded to : study transcripts of games, infer the > rules of > the games from the transcripts, and then play the games... but that > could do > *nothing* else > > Such a software system would be VASTLY superior to any existing AI > software > system. But if it could do nothing else, it would still be terribly > overspecialized and narrow compared to a human... > > I would see such a system as halfway between Deep Blue and humans, > in terms > of general intelligence. > > -- Ben G > > ------- > To unsubscribe, change your address, or temporarily deactivate your > subscription, > please go to > http://v2.listbox.com/member/?[EMAIL PROTECTED] > ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
