Evolution of hyperheuristics for the biobjective 0/1 knapsack problem by multiobjective genetic programming

  • Authors:

  • Rajeev Kumar;Ashwin H. Joshi;Krishna K. Banka;Peter I. Rockett

  • Affiliations:

  • Indian Institute of Technology Kharagpur, Kharagpur, India;Indian Institute of Technology Kharagpur, Kharagpur, India;Indian Institute of Technology Kharagpur, Kharagpur, India;University of Sheffield, Sheffield, United Kngdm

  • Venue:
  • Proceedings of the 10th annual conference on Genetic and evolutionary computation
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The 0/1 knapsack problem is one of the most exhaustively studied NP-hard combinatorial optimization problems. Many different approaches have been taken to obtain an approximate solution to the problem in polynomial time. Here we consider the biobjective 0/1 knapsack problem. The contribution of this paper is to show that a genetic programming system can evolve a set of heuristics that can give solutions on the Pareto front for multiobjective combinatorial problems. The genetic programming (GP) system outlined here evolves a heuristic which decides whether or not to add an item to the knapsack in such a way that the final solution is one of the Pareto optimal solutions. Moreover, the Pareto front obtained from the GP system is comparable to the front obtained from other human-designed heuristics. We discuss the issue of the diversity of the obtained Pareto front and the application of strongly-typed GP as a means of obtaining better diversity.