mnof function

Helper function to create numeric multi-objective optimization test function.

This is a simplifying wrapper around makeMultiObjectiveFunction. It can be used if the function to generate is purely numeric to save some lines of code.

mnof(
  name = NULL,
  id = NULL,
  par.len = NULL,
  par.id = "x",
  par.lower = NULL,
  par.upper = NULL,
  n.objectives,
  description = NULL,
  fn,
  vectorized = FALSE,
  noisy = FALSE,
  fn.mean = NULL,
  minimize = rep(TRUE, n.objectives),
  constraint.fn = NULL,
  ref.point = NULL
)

Arguments

• name: [character(1)]

  Function name. Used for the title of plots for example.

• id: [character(1) | NULL]

  Optional short function identifier. If provided, this should be a short name without whitespaces and now special characters beside the underscore. Default is NULL, which means no ID at all.

• par.len: [integer(1)]

  Length of parameter vector.

• par.id: [character(1)]

  Optional name of parameter vector. Default is x .

• par.lower: [numeric]

  Vector of lower bounds. A single value of length 1 is automatically replicated to n.pars. Default is -Inf.

• par.upper: [numeric]

  Vector of upper bounds. A singe value of length 1 is automatically replicated to n.pars. Default is Inf.

• n.objectives: [integer(1)]

  Number of objectives of the multi-objective function.

• description: [character(1) | NULL]

  Optional function description.

• fn: [function]

  Objective function.

• vectorized: [logical(1)]

  Can the objective function handle vector input, i.~e., does it accept matrix of parameters? Default is FALSE.

• noisy: [logical(1)]

  Is the function noisy? Defaults to FALSE.

• fn.mean: [function]

  Optional true mean function in case of a noisy objective function. This functions should have the same mean as fn.

• minimize: [logical]

  Logical vector of length n.objectives indicating if the corresponding objectives shall be minimized or maximized. Default is the vector with all components set to TRUE.

• constraint.fn: [function | NULL]

  Function which returns a logical vector indicating whether certain conditions are met or not. Default is NULL, which means, that there are no constraints beside possible box constraints defined via the par.set argument.

• ref.point: [numeric]

  Optional reference point in the objective space, e.g., for hypervolume computation.

Examples

# first we generate the 10d sphere function the long way
fn = makeMultiObjectiveFunction(
  name = "Testfun",
  fn = function(x) c(sum(x^2), exp(sum(x^2))),
  par.set = makeNumericParamSet(
    len = 10L, id = "a",
    lower = rep(-1.5, 10L), upper = rep(1.5, 10L)
  ),
  n.objectives = 2L
)

# ... and now the short way
fn = mnof(
 name = "Testfun",
 fn = function(x) c(sum(x^2), exp(sum(x^2))),
 par.len = 10L, par.id = "a", par.lower = -1.5, par.upper = 1.5,
 n.objectives = 2L
)