🚀 go-pugleaf

I'm posting this, because mail bounced...

>>
>>If someone could give further pointers (explicit references would be very
>>nice indeed) to any written material on the subject of Darwinian software I'd
>>appreciate it. Also, what has been done and what is being done right now?
>>

One type of "Darwinian" software involves what has come to be called
"Genetic Algorithms".  An early reference for these is

Holland, J. H. (1975).  Adaptation in natural and artificial systems.
Ann Arbor, MI: University of Michigan Press.

There are also a few papers on genetic algorithms in

(1988) Proceedings of the Fifth International Conference on Machine Learning.
Ann Arbor, MI: Morgan Kaufmann.

You should be able to get additional references from these papers.
In addition, there have been some problem-solving systems that use
an evolutionary-type approach to learning preconditions on rules.  The basic
idea is to create new rules by generalizing, discriminating, and composing old
ones, and then letting the rules compete, strengthening rules that proved to
be useful.  You might want to look at Anderson's ACT* system, and Holland, et
al.'s PI system, and Langley's SAGE.

Anderson, J. R. (1983).  The architecture of cognition.  Cambridge, MA:
Harvard University Press.

Holland, J. H., Holyoak, K. J., Nisbett, R. E., & Thagard, P. R. (1986).
Induction: Processes of inference, learning, and discovery.  Cambridge, MA:
MIT Press.

Langley, P. (1985).  Learning to search: From weak methods to domain-specific
heuristics.  Cognitive Science, 9, 217-260.