Disclaimer: OOPS has nothing to do with Genetic Programming etc
1985: Cramer invents GP: given some goal, use genetic algorithms / evolution to evolve tree-like or string-like programs
1987: world’s second paper on GP, by undergrads Schmidhuber, Dickmanns, Winklhofer
1990: someone else manages to patent GP despite the prior art (remains unchallenged because there is little commercial interest in GP)
Astonishingly, most existing GP implementations ignore basic motivation for search in program space: no loops, no recursion! Many GP authors seem proud of solving problems such as 20 bit parity; most GP papers have appeared at conferences with near-zero rejection rate
GP is a fun heuristic, but without theoretical foundation: no bias-optimality, no principled way of allocating runtime to programs & of reusing previous code, etc…
But we may use GP as a primitive for OOPS, of course
Back to J. Schmidhuber's OOPS page