An A* like algorithm to improve the performance of genetic algorithms

Genetic algorithms (GAs) often suffer from difficulties of convergence due to lack of guidelines for the selection process. Normally the selection is based on the current fitness of the individuals, evaluated by a fitness function. However, the present fitness of an individual need not always indicate its ability to improve further. In this work, we propose an A* like evaluation method, which takes into account not only the present fitness of the individual, but also an estimate of its scope for further improvisation. This simple improvement to simple GA has produced results comparable to specialised GA methods in selection problems.