Reinforcement Learning and Biologically Inspired Artificial Neural Networks

Over the last few years, machine learning methods have used Deep Neural Network architectures to tackle complex problems. In this paper, we applied biologically inspired neural machine learning to solve two classical and well-known challenging problems, the Mountain Car Continuous and the Cart Pole. We use a neural network extracted from the connectome of C-Elegans to learn a policy able to yield a good solution. We used Reinforcement Learning (RL) and optimization techniques to train the models, in addition to proposing a novel neural dynamics model. We use different metrics to make a detailed comparison of the results obtained, combining different neuronal dynamics and optimization methods. We obtained very competitive results compared with the solution provided in the literature, particularly with the novel dynamic neuronal model.