> slowly vary parameters to evolve it to be more robust
Injecting noise and other constraints (like forcing it place circuits in different parts of the device) are totally valid when it needs to evolve in-place.
For the most part, I think it would be better to run in a simulator where it can evolve against an abstract model, then it couldn't overfit to the specific device and environment. This doesn't work if the best simulator of the system is the system itself.
Agreed, but to some degree relying on a simulator means it can no longer evolve truly novel solutions. No simulator would have accurately simulated many of the effects it was leveraging in the lab. Essentially you would only generate efficient uses of concepts we already know how to model / engineer well. Using the setup he used, it can generate things we don't understand well and can take advantage of. Or begin to study better.
Injecting noise and other constraints (like forcing it place circuits in different parts of the device) are totally valid when it needs to evolve in-place.
For the most part, I think it would be better to run in a simulator where it can evolve against an abstract model, then it couldn't overfit to the specific device and environment. This doesn't work if the best simulator of the system is the system itself.
https://en.wikipedia.org/wiki/Robust_optimization
https://www2.isye.gatech.edu/~nemirovs/FullBookDec11.pdf
Robust Optimization https://www.youtube.com/watch?v=-tagu4Zy9Nk