Genetic planning using variable length chromosomes

Abstract

This paper describes a genetic planning system, i.e., a program capable of solving planning problems us-ing evolutionary techniques. As opposed to other ap-proaches in Genetic Planning, we use a variable length chromosomes model in addition to a complex tness function and several enhancements of the Simple Ge-netic Algorithm (Holland 1975), such as multipopula-tions, population reset, weak memetism, tournament se-lection and elitist genetic operators. Our genetic planner is tested on standard planning domains and problems (described in PDDL), is used for parameter and per-formance analysis, and is compared to previous work. Results show efciency in memory management and greater solving power than the predecessors'.