spotOptimizationInterfaceMco

Description

This function is an interface fashioned like the optim function. It is used in SPOT to access several different multi-criteria optimization methods.

Usage

1
2
spotOptimizationInterfaceMco(par, fn, gr = NULL, lower, upper, method,
  control, ref, ...)

Arguments

par

is a point (vector) in the decision space of fn, par is not used (yet)

fn

is the target function of type y = f(x, ...)

gr

gradient function, gr is not used (yet)

lower

is a vector that defines the lower boundary of search space

upper

is a vector that defines the upper boundary of search space

method

is a string that describes which method is to be used, as implemented in this function. Else it can be a function, which is a custom optimization function created by the user. See details.

control

is a list of additional settings. See details.

ref

reference point. Please provide this even with methods that do not use it (e.g. "nsga2"), to specify the dimension of the objective space.

...

additional parameters to be passed on to fn

Details

The control list contains:
fevals stopping criterion, number of evaluations allowed for fn (defaults to 100)
popsize population size or number of particles (default depends on method)
restarts whether or not to do restarts, default is FALSE
Also note that the parameter method will be used to choose the optimization method from the following list:
"nsga2" - the nsga2 function from the mco Package
"sms-emoa" - The basic sms-emoa in the SPOT package
All of the above methods use bound constraints. For references and details on the specific methods, please check the documentation of the packages that provide them.

Furthermore, the user can choose to use a function instead of a string for the method. The used function should have the same parameters and arguments as documented for this very function, i.e. spotOptimizationInterfaceMco.

Value

This function returns a list with:
par parameters of the found solutions, e.g. the Pareto set
value target function values of the found solutions, e.g. the Pareto front
counts number of evaluations of fn

See Also

spotOptimizationInterface spotOptim

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.