Ah, found Lenant's fleet:
LINK%20-%20Professor%20Lenat%20and%20EURISKO's%20Winning%20Fleet.htm)
This is partly for my own reference. May as well cut and paste the whole thing in case the link goes bad:
Winning TCS fleet - TL 12
Four Garter class: TB-Garter TB-K1567F3-B41106-34009-1 MCr 17,584.104 Bearing C 1 EE 7 12,000 tons Batteries C 1 EE 7 crew=170 Agility=4; Fuel=840; Cargo=4.3 low=170 Note: L-Hyd drop tanks add 6000 tons of fuel and mass,change the agility to 4, and cost MCr6.01.(TB-K1344F3) The ship is designed to manuever when carrying up to 72,000 tons of drop tanks and one Wasp fighter.
Four Cisor class: BD-Cisor BD-K9525F3-E41100-340C5-0 MCr22,291.175 Bearing 1 11 1U 19,980 tons Batteries 1 11 1U crew= ? Agility=0; Fuel=999; Cargo=19.1 low=95 Note: L-Hyd drop tanks add 9,990 tons of fuel and mass, and cost MCr10. (BD- L9313F3) The ship is designed to manuever when carrying up to 29,970 tons of drop tanks.
Three Queller class: BH-Queller BH-K1526F3-B41106-34Q02-1 MCr27,802.392 Bearing Z 1 NN1 N 19,600 tons Batteries Z 1 NN1 N crew=263 Agility=0; Fuel=1,176; Cargo=10.72 low=232; marines=200 Note: L-hyd drop tanks add 9,800 tons of fuel and mass, and cost MCr9.81. (BH-L1314F3) The ship is designed to manuever when carrying up to 29,400 tons of drop tanks and two fighters (one Wasp and one Bee).
Seventy-five Eurisko class: BA-Eurisko Ba-K952563-J41100-34003-0 MCr13,030.385 Bearing 1 11 V 11,100 tons Batteries 1 11 V crew=131 Agility=2; Fuel=555; Cargo=8 low=0; marines=35 Note: L-hyd drop tanks add 5,550 tons of fuel and mass, change the agility to 1, and cost 5.56. (BA-K931363) The ship is designed to manuever when carrying up to 16,650 tons of drop tanks.
Seven Wasp class: IL-Wasp Il-A90ZZF2-J00000-00009-0 MCr896.75 Bearing 1 1,000 tons Batteries 1 Crew=19 Agility=6; Fuel=60; Cargo=0 low=0
Three Bee class: FF-Bee FF-0906661-A30000-00001-0 MCr127.945 Bearing 1 2 99 tons Batteries 1 2 crew=2 Agility=0; Fuel=5.94; Cargo=0
Douglas Lenat's program EURISKO is legendary in the AI community for a distinct real-world achievement: allowing Lenat to win the the Traveller TCS roleplaying game tournament two years in a row (and then semi-voluntarily not competing subsequent years). Lenat never released EURISKO's source code, leaving how he managed to pull off this feat somewhat of a mystery. Yet Lenat's later work based on EURISKO does not seem to have yielded anything else in the way of practical benefits.
Some time ago on LessWrong, someone proposed trying to figure out what Lenat did and reimplementing EURISKO. But Eliezer is worried this could be dangerous. So I have another proposal: see if Lenat's accomplishment can be replicated using machine learning and genetic programming techniques that are already publicly known.
My suspicion is that Lenat's TCS win tells us more about TCS than about EURISKO, that TCS is likely a game that's inherently vulnerable to the "find winning strategies by simulating a lots of games on a computer" meta-strategy. I've heard, for example, that battles are often tactically trivial, with the outcome of battles effectively determined by the composition of the two fleets (and fleet composition is what Lenat used EURISKO for). If that hypothesis is correct, though, it suggests it shouldn't be necessary to reimplement EURISKO specifically to get a program that's good at designing TCS fleets. If that turns out not to be the case, it would be evidence that there really is something special about EURISKO after all.
Does anyone know if anyone has tried this? As a novice computer programmer, I think it might be a good project to hone my programming skills. Input on how to approach such a project would be appreciated.