Genetic-Gated Networks for Deep Reinforcement
This is an incremental method for reinforcement learning practitioners seeking better sample efficiency and performance.
The authors tackled the problem of improving sample efficiency and performance in reinforcement learning by introducing Genetic-Gated Networks (G2Ns), which combine binary genetic genes with neural networks to leverage both gradient-free and gradient-based optimization, resulting in a large improvement.
We introduce the Genetic-Gated Networks (G2Ns), simple neural networks that combine a gate vector composed of binary genetic genes in the hidden layer(s) of networks. Our method can take both advantages of gradient-free optimization and gradient-based optimization methods, of which the former is effective for problems with multiple local minima, while the latter can quickly find local minima. In addition, multiple chromosomes can define different models, making it easy to construct multiple models and can be effectively applied to problems that require multiple models. We show that this G2N can be applied to typical reinforcement learning algorithms to achieve a large improvement in sample efficiency and performance.