MULTIPHASE GENETIC PROGRAMMING: A CASE STUDY IN SUMO MANEUVER EVOLUTION
Jiming Liu, Shiwu Zhang · International Journal of Pattern Recognition and Artificial Intelligence · 2004
In this paper, we describe a new evolutionary computation approach, called multiphase genetic programming (MPGP). The special features of this approach lie in its variable-granularity representations of chromosomes and their corresponding genetic operations. In the paper, we provide an overview of the MPGP approach as well as details on how the sumo maneuver evolution experiments are carried out and how the MPGP-based case study differs from others.