تقرير
Deep Neural Crossover
| العنوان: | Deep Neural Crossover |
|---|---|
| المؤلفون: | Shem-Tov, Eliad, Elyasaf, Achiya |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Neural and Evolutionary Computing |
| الوصف: | 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. Comment: 7 pages, 3 figures, 4 tables. Published by the Genetic and Evolutionary Computation Conference (GECCO 2024) |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1145/3638529.365402 |
| URL الوصول: | http://arxiv.org/abs/2403.11159 |
| رقم الأكسشن: | edsarx.2403.11159 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1145/3638529.365402 |
|---|