I read the JavaDocs and now I understand how the SimulatedAnnealing code handles multiple objectives. I know this won't work for my use case because my objectives are not linearly dependent.
There are a few approaches to multi-object simulated annealing. MOSA by Smith et.al. is one:
Has anyone written code like this for Opt4j before? If not, and if there is an interest, I could try writing some if there is a team member who could help finish it.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I read the JavaDocs and now I understand how the SimulatedAnnealing code handles multiple objectives. I know this won't work for my use case because my objectives are not linearly dependent.
There are a few approaches to multi-object simulated annealing. MOSA by Smith et.al. is one:
http://www.researchgate.net/publication/3419046_Dominance-Based_Multiobjective_Simulated_Annealing/links/02e7e5256f742a2a8d000000
http://www.kismith.co.uk/files/tmp/cec2004-talk.pdf
Has anyone written code like this for Opt4j before? If not, and if there is an interest, I could try writing some if there is a team member who could help finish it.
Dear Courtney, did you start working on the MOSA? - Is there any help required so far.
If you want to contribute code to Opt4J, this is also possible.