Efficient representation of Recurrent Neural Networks for markovian/non-markovian non-linear control problems

A novel representation of Recurrent Artificial neural network is proposed for non-linear markovian and non-markovian control problems. The network architecture is inspired by Cartesian Genetic Programming. The neural network attributes namely weights, topology and functions are encoded using Cartesian Genetic Programming. The proposed algorithm is applied on the standard benchmark control problem: double pole balancing for both markovian and non-markovian cases. Results demonstrate that the network has the ability to generate neural architecture and parameters that can solve these problems in substantially fewer number of evaluations in comparison to earlier neuroevolutionary techniques. The power of Recurrent Cartesian Genetic Programming Artificial Neural Network (RCGPANN) is its representation which leads to a thorough evolutionary search producing generalized networks.