Skip to yearly menu bar Skip to main content


Poster

Genetic-Gated Networks for Deep Reinforcement Learning

Simyung Chang · John Yang · Jaeseok Choi · Nojun Kwak

Room 517 AB #136

Keywords: [ Combinatorial Optimization ] [ Multi-Agent RL ] [ Reinforcement Learning ]


Abstract:

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.

Live content is unavailable. Log in and register to view live content