Evolution of Fitness Functions to Improve Heuristic Performance

In this paper we introduce the variable fitness function which can be used to control the search direction of any search based optimisation heuristic where more than one objective can be defined, to improve heuristic performance. The method is applied to a multi-objective travelling salesman problem and the performance of heuristics enhanced with the variable fitness function is compared to the original heuristics, yielding significant improvements. The structure of the variable fitness functions is analysed and the search is visualised to better understand the process.

• Type: Conference
• Year: 2007
• Where: LION
• Authors: Stephen Remde, Peter I. Cowling, Keshav P. Dahal, Nic Colledge
• Keywords: Heuristics, LION 2007, Search Based Optimisation, Variable Fitness Functions