We present a novel multi-parent crossover operator in genetic algorithms (GAs) called ``Deep Neural Crossover'' (DNC). Unlike conventional GA crossover operators that rely on a random selection of parental genes, DNC leverages the capabilities of deep reinforcement learning (DRL) and an encoder-decoder architecture to select the genes. Specifically, we use DRL to learn a policy for selecting promising genes. The policy is stochastic, to maintain the stochastic nature of GAs, representing a distribution for selecting genes with a higher probability of improving fitness. Our architecture features a recurrent neural network (RNN) to encode the parental genomes into latent memory states, and a decoder RNN that utilizes an attention-based pointing mechanism to generate a distribution over the next selected gene in the offspring. To improve the training time, we present a pre-training approach, wherein the architecture is initially trained on a single problem within a specific domain and then applied to solving other problems of the same domain. We compare DNC to known operators from the literature over two benchmark domains -- bin packing and graph coloring. We compare with both two- and three-parent crossover, outperforming all baselines. DNC is domain-independent and can be easily applied to other problem domains.

翻译：我们提出了一种新颖的遗传算法多父代交叉算子——“深度神经交叉”（DNC）。与传统依赖随机选择父代基因的遗传算法交叉算子不同，DNC利用深度强化学习（DRL）和编码器-解码器架构来筛选基因。具体而言，我们通过DRL学习一个策略，用于选择具有潜力的基因。该策略具有随机性，以保持遗传算法的随机特性，它表示一个基因选择分布，其中选择能更有效提升适应度的基因的概率更高。我们的架构采用循环神经网络（RNN）将父代基因组编码为隐式记忆状态，同时使用基于注意力指针机制的解码器RNN生成子代候选基因的分布概率。为缩短训练时间，我们提出了一种预训练方法：先针对特定领域的单个问题对架构进行初始训练，再将其应用于同一领域的其他问题求解中。我们选取两个基准领域——装箱问题与图着色问题，将DNC与文献中已知算子进行对比。通过与双亲及三亲交叉方法的比较，DNC在所有基线方法中表现最优。该算子具有领域无关性，可便捷地应用于其他问题领域。