Hyper-heuristics and classifier systems for solving 2D-regular cutting stock problems

摘要: This paper presents a method for combining concepts of Hyper-heuristics and Learning Classifier Systems solving 2D Cutting Stock Problems. The idea behind is to discover some combination straightforward heuristics solve wide range problems. To be worthwhile, such should outperform the single heuristics. In this paper, Hyper-heuristic formed using XCS-type System which learns solution procedure when individual XCS evolves behavior model determines possible actions (selection placement heuristics) given states problem. When tested with collection different problems, finds very competitive results most cases. testebed composed problems used in other similar studies literature. Some additional instances testbed were randomly generated.