Biased Initialization

Biased Initialization#

One way of customizing an algorithm is a biased initial population. This can be very helpful if expert knowledge already exists, and known solutions should be improved. In the following, two different ways of initialization are provided: a) just providing the design space of the variables and b) a Population object where the objectives and constraints are provided and do not need to be calculated again.

NOTE: This works with all population-based algorithms in pymoo. Technically speaking, all algorithms which inherit from GeneticAlgorithm. For local-search based algorithm, the initial solution can be provided by setting x0 instead of sampling.

By Array#

[1]:

import numpy as np

from pymoo.algorithms.moo.nsga2 import NSGA2
from pymoo.problems import get_problem
from pymoo.optimize import minimize

problem = get_problem("zdt2")

X = np.random.random((300, problem.n_var))

algorithm = NSGA2(pop_size=100, sampling=X)

minimize(problem,
         algorithm,
         ('n_gen', 10),
         seed=1,
         verbose=True)

==========================================================================
n_gen  |  n_eval  | n_nds  |      igd      |       gd      |       hv
==========================================================================
     1 |      300 |     12 |  3.5513115138 |  3.9760489486 |  0.000000E+00
     2 |      400 |     11 |  3.5513115138 |  3.9273884740 |  0.000000E+00
     3 |      500 |     11 |  2.8951504930 |  3.7656060256 |  0.000000E+00
     4 |      600 |      6 |  2.8951504930 |  3.2826949452 |  0.000000E+00
     5 |      700 |      6 |  2.8951504930 |  3.1708123316 |  0.000000E+00
     6 |      800 |      5 |  2.8951504930 |  3.2548673229 |  0.000000E+00
     7 |      900 |      9 |  2.7285748978 |  2.9356138941 |  0.000000E+00
     8 |     1000 |      5 |  2.4583365933 |  2.7465700598 |  0.000000E+00
     9 |     1100 |      9 |  2.4419556130 |  2.5012801731 |  0.000000E+00
    10 |     1200 |      8 |  2.2447405753 |  2.4139170936 |  0.000000E+00

[1]:

<pymoo.core.result.Result at 0x76270f4bb390>

By Population (pre-evaluated)#

[2]:

import numpy as np

from pymoo.algorithms.moo.nsga2 import NSGA2
from pymoo.problems import get_problem
from pymoo.core.evaluator import Evaluator
from pymoo.core.population import Population
from pymoo.optimize import minimize

problem = get_problem("zdt2")

# create initial data and set to the population object
X = np.random.random((300, problem.n_var))
pop = Population.new("X", X)
Evaluator().eval(problem, pop)

algorithm = NSGA2(pop_size=100, sampling=pop)

minimize(problem,
         algorithm,
         ('n_gen', 10),
         seed=1,
         verbose=True)

==========================================================================
n_gen  |  n_eval  | n_nds  |      igd      |       gd      |       hv
==========================================================================
     1 |        0 |      7 |  3.1485569015 |  3.6299859113 |  0.000000E+00
     2 |      100 |      8 |  3.1485569015 |  3.5345318848 |  0.000000E+00
     3 |      200 |      8 |  3.1297820336 |  3.2821583628 |  0.000000E+00
     4 |      300 |     11 |  2.9391437524 |  3.1783149160 |  0.000000E+00
     5 |      400 |      6 |  2.7344934650 |  3.0635716922 |  0.000000E+00
     6 |      500 |     13 |  2.3791000489 |  2.6773229576 |  0.000000E+00
     7 |      600 |     11 |  2.2942052178 |  2.6151395433 |  0.000000E+00
     8 |      700 |     12 |  2.0591994531 |  2.5336571674 |  0.000000E+00
     9 |      800 |     15 |  1.9055932098 |  2.4678777539 |  0.000000E+00
    10 |      900 |     11 |  1.7780927497 |  1.9921858118 |  0.000000E+00

[2]:

<pymoo.core.result.Result at 0x762703157750>
Contents