GENetic ImplemenTOR (GENITOR)

class pypop7.optimizers.ga.genitor.GENITOR(problem, options)[source]

GENetic ImplemenTOR (GENITOR).

Note

“Selective pressure and population diversity should be controlled as directly as possible.”—[Whitley, 1989]

This is a slightly modified version of GENITOR for continuous optimization. Originally GENITOR was proposed to solve challenging neuroevolution problems by Whitley, the recipient of IEEE Evolutionary Computation Pioneer Award 2022.

Parameters:

  • problem (dict) –

    problem arguments with the following common settings (keys):

    • ’fitness_function’ - objective function to be minimized (func),

    • ’ndim_problem’ - number of dimensionality (int),

    • ’upper_boundary’ - upper boundary of search range (array_like),

    • ’lower_boundary’ - lower boundary of search range (array_like).

  • options (dict) –

    optimizer options with the following common settings (keys):

    • ’max_function_evaluations’ - maximum of function evaluations (int, default: np.Inf),

    • ’max_runtime’ - maximal runtime to be allowed (float, default: np.Inf),

    • ’seed_rng’ - seed for random number generation needed to be explicitly set (int);

    and with the following particular setting (key):

    • ’n_individuals’ - population size (int, default: 100),

    • ’cv_prob’ - crossover probability (float, default: 0.5).

Examples

Use the optimizer to minimize the well-known test function Rosenbrock:

 1>>> import numpy
 2>>> from pypop7.benchmarks.base_functions import rosenbrock  # function to be minimized
 3>>> from pypop7.optimizers.ga.genitor import GENITOR
 4>>> problem = {'fitness_function': rosenbrock,  # define problem arguments
 5...            'ndim_problem': 2,
 6...            'lower_boundary': -5*numpy.ones((2,)),
 7...            'upper_boundary': 5*numpy.ones((2,))}
 8>>> options = {'max_function_evaluations': 5000,  # set optimizer options
 9...            'seed_rng': 2022}
10>>> genitor = GENITOR(problem, options)  # initialize the optimizer class
11>>> results = genitor.optimize()  # run the optimization process
12>>> # return the number of function evaluations and best-so-far fitness
13>>> print(f"GENITOR: {results['n_function_evaluations']}, {results['best_so_far_y']}")
14GENITOR: 5000, 0.004382445279905116

For its correctness checking of coding, the code-based repeatability report cannot be provided owing to the lack of its simulation environment.

cv_prob

crossover probability.

Type:

float

n_individuals

population size.

Type:

int

References

https://www.cs.colostate.edu/~genitor/

Whitley, D., Dominic, S., Das, R. and Anderson, C.W., 1993. Genetic reinforcement learning for neurocontrol problems. Machine Learning, 13, pp.259-284. https://link.springer.com/article/10.1023/A:1022674030396

Whitley, D., 1989, December. The GENITOR algorithm and selection pressure: Why rank-based allocation of reproductive trials is best. In Proceedings of International Conference on Genetic Algorithms (pp. 116-121). https://dl.acm.org/doi/10.5555/93126.93169