我写了一个简单的遗传算法，代码如下
适应度函数定义为

def fitness(a, b, c, d, e):
    return a**2 + b**2 + c**2 + d**2 + e**2

生成第一群体的函数

def generate_pop(numInd, numGene):
    population = []
    for i in range(numInd):
        individual = [random.uniform(-10, 10) for _ in range(numGene)]
        population.append(individual)
    return population

选择和交叉功能

def randomCrossover(population):
    offspring = []
    for i in range(len(population)//2):
        Ind1_index = random.randint(0, len(population)-1)
        Ind2_index = random.randint(0, len(population)-1)
        while Ind2_index == Ind1_index:
            Ind2_index = random.randint(0, len(population)-1)

        Ind1 = population[Ind1_index]
        Ind2 = population[Ind2_index]

        crossPoint = random.randint(1, len(Ind1))
        child1 = Ind1[:crossPoint] + Ind2[crossPoint:]
        child2 = Ind2[:crossPoint] + Ind1[crossPoint:]
        offspring.append(child1)
        offspring.append(child2)
    return offspring

结束此函数中的所有函数

def geneticAlgorithm(mutation=0.1, numGeneration=100):
    population = generate_pop(12, 5)
    maxFitnessScoreGen = []
    minFitnessScoreGen = []
    avgFitnessScoreGen = []
    for _ in range(numGeneration):
        fitScore = [fitness(a, b, c, d, e) for a, b, c, d, e in population]
        maxFitnessScoreGen.append(max(fitScore))
        minFitnessScoreGen.append(min(fitScore))
        avgFitnessScoreGen.append(mean(fitScore))
        # population = [population[i] for i in range(len(population)) if fitness[i] == min(fitness)] # should individual that have lowest fitness score
        
        offspring = randomCrossover(population)
            
        for i in range(len(offspring)):
            if random.uniform(0, 1) < mutation:
                offspring[i] = [random.uniform(-10, 10), random.uniform(-10, 10), random.uniform(-10, 10), random.uniform(-10, 10), random.uniform(-10, 10)]

        population = offspring
        # print(f'gen {_} maxScore = {maxFitnessScoreGen}, avgScore = {avgFitnessScoreGen}')
        # print(population)

    return maxFitnessScoreGen, minFitnessScoreGen ,avgFitnessScoreGen

但优化的结果是振荡，似乎没有改善。我不知道我做错了我的代码。