A generation is one cycle of a genetic algorithm: evaluate a population of candidate solutions, select parents, create replacement individuals, and apply possible mutations. section 5.3 section 5.1
A generic generation proceeds through these operations:
- Measure each chromosome’s fitness and stop early when one reaches the target threshold. section 5.3
- Select parents using roulette-wheel or tournament selection. section 5.3
- Reproduce children through crossover, replace the population, and possibly mutate every individual. section 5.3
Tracking progress with SimpleEquation
A run seeking the maximum of 6x − x² + 4y − y² improved across generations and reached x = 3, y = 2, with fitness 13 after 18 generations. Each generation reported its best and average fitness. section 5.4
Use the outline to inspect how evaluation, selection, reproduction, and mutation form a repeating generation cycle. section 5.3
