Deep Learning Evolution: Using Genetic Algorithm to Modify Training Datasets

The work addresses the problem of integration of deep learning and genetic algorithms (GA). An approach is developed where the GA directly modifies the training datasets rather than adjusting the parameters of the trained neural network. These datasets consist of records capturing the agent's behavior in the environment and are treated as genotypes within the GA framework. The resulting phenotypes are the trained neural networks themselves. Importantly, the architecture and hyperparameters of the neural network and its learning model remain unchanged throughout the process. Numerical experiments conducted using the “Three Cowboys” game paradigm provide evidence supporting the concept and demonstrate the effectiveness of the proposed approach.