Abstract:
Nowadays, scheduling problems arise in almost
all areas of human activity. To handle the complexity
of the real world scheduling problems, many
researchers have been invested over the years.
Currently research is being directed to raise the level
of generality. Therefore, this has led to the
development of hyper heuristics system. A hyper
heuristic is high level problem solving methodology
that performs a search over the space generated by a
set of low level heuristics. A motivating goal of hyper
heuristic research is to create automated techniques
that applicable to a wide range of problems with
different characteristics. One of the hyper heuristic
frameworks is based on a single point search
containing two main stages: heuristic selection and
move acceptance. By using exam timetabling
problem as a test bed, this paper proposes the non
linear great deluge hyper heuristic with
reinforcement learning method to intend to improve
the performance of hyper heuristic
