mutPolynomial function

Polynomial mutation.

Performs an polynomial mutation as used in the SMS-EMOA algorithm. Polynomial mutation tries to simulate the distribution of the offspring of binary-encoded bit flip mutations based on real-valued decision variables. Polynomial mutation favors offspring nearer to the parent.

mutPolynomial(ind, p = 0.2, eta = 10, lower, upper)

Arguments

• ind: [numeric]

  Numeric vector / individual to mutate.

• p: [numeric(1)]

  Probability of mutation for each gene of an offspring. In other words, the probability that the value (allele) of a given gene will change. Default is 0.2

• eta: [numeric(1)

  Distance parameter to control the shape of the mutation distribution. Larger values generate offspring closer to the parents. Default is 10.

• lower: [numeric]

  Vector of minimal values for each parameter of the decision space. Must have the same length as ind.

• upper: [numeric]

  Vector of maximal values for each parameter of the decision space. Must have the same length as ind.

Returns

[numeric]

References

[1] Deb, Kalyanmoy & Goyal, Mayank. (1999). A Combined Genetic Adaptive Search (GeneAS) for Engineering Design. Computer Science and Informatics. 26. Retrieved from http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.27.767&rep=rep1&type=pdf

See Also

Other mutators: mutBitflip(), mutGauss(), mutInsertion(), mutInversion(), mutJump(), mutScramble(), mutSwap(), mutUniform()