A python implementation of NSGA-II multi-objective optimization algorithm.
Original paper see here.
Following 2 GIFs visulize the optimization process (10 iterations) of multi-objective problem:
- min f_1(x) = (x-400)*(x-400)
- min f_2(x) = (x-600)*(x-600)
x belongs to the set of real numbers. The first GIF show the change of Pareto front while the second one shows that of population's performance on 2 objective funcs.
Pareto front
Objective funcs value
Requirements:
- numpy
- matplotlib