WFG Benchmarks

The WFG (Walking Fish Group) benchmark collection contains all functions from the WFG benchmark suite. Python implementation of the original C++ code is derived from the optproblems python library.

Sources:

Huband, S.; Hingston, P.; Barone, L.; While, L. (2006). A review of multiobjective test problems and a scalable test problem toolkit. IEEE Transactions on Evolutionary Computation, vol.10, no.5, pp. 477-506.

Available Problems

  • bocode.Synthetics.WFG.WFG1

  • bocode.Synthetics.WFG.WFG2

  • bocode.Synthetics.WFG.WFG3

  • bocode.Synthetics.WFG.WFG4

  • bocode.Synthetics.WFG.WFG5

  • bocode.Synthetics.WFG.WFG6

  • bocode.Synthetics.WFG.WFG7

  • bocode.Synthetics.WFG.WFG8

  • bocode.Synthetics.WFG.WFG9

Example Usage

import bocode
import torch

# Retrieve available dimensions for instantiation
available_dimensions = bocode.Synthetics.WFG.WFG1.available_dimensions

# Create a WFG benchmark problem
problem = bocode.Synthetics.WFG.WFG1(dim=5)

# Get problem information
bounds = problem.bounds

# Evaluate at a point
x = torch.Tensor([[0.0] * problem.dim])
values, constraints = problem.evaluate(x)

print(f"First WFG function values at origin: {values[0]}")

Output:

First WFG function values at origin: tensor([1., 5.])