We present a novel approach to performing fitness approximation in genetic
algorithms (GAs) using machine-learning (ML) models, focusing on evolutionary
agents in Gymnasium (game) simulators -- where fitness computation is costly.
Maintaining a dataset of sampled individuals along with their actual fitness
scores, we continually update throughout an evolutionary run a
fitness-approximation ML model. We compare different methods for: 1) switching
between actual and approximate fitness, 2) sampling the population, and 3)
weighting the samples. Experimental findings demonstrate significant
improvement in evolutionary runtimes, with fitness scores that are either
identical or slightly lower than that of the fully run GA -- depending on the
ratio of approximate-to-actual-fitness computation. Our approach is generic and
can be easily applied to many different domains.

我们提出了一种新的方法，在遗传算法中使用机器学习模型进行适应度近似估计，重点是在 Gymnasium（游戏）模拟器中的进化智能体，其中适应度计算代价很高。维护一个包括个体及其实际适应度评分的样本数据集，我们通过整个进化过程不断更新适应度近似估计的机器学习模型。我们比较了不同的方法：1）在实际适应度和近似适应度之间切换，2）对种群进行抽样，并且 3）对样本进行加权。实验结果表明，在适应度近似与实际计算的比率下，进化运行时间得到了显著的改善，且适应度评分要么相同，要么略低于完整运行的遗传算法。我们的方法是通用的，并且可以轻松应用于许多不同的领域。