A good step would be looking at Lenat's published work around that time to get a feel for how he thought about AI and what strategies he was likely to implement. Lenat was a firm believer in symbolics meaning he worked almost entirely in Lisp. Another thing is that his systems were interactive - they relied to a large degree on user input, possibly in 'selecting' the right strategies which the machine would then investigate in further depth and possibly try to optimize. For an example of this, rule 2 of the AM system is, "If the user has recently referred to X, then boost the priority of any tasks involving X."
Lenat himself said that the Traveller TCS solution was 60% himself and 40% Eurisko, and given that he was trying to promote his software, this is probably an overestimate. It's likely that Lenat won Traveller TCS, not Eurisko, and that Eurisko was simply a tool he used to carry out various simulations and computations that would have been tedious to do by hand. That doesn't mean that the system is useless though. I'm personally extremely interested in interactive AI systems that use the 'best of both worlds', relying on a combination of human intuition and raw machine computational power to perform tasks that neither could have done separately.
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.