Neural Networks with Online Sequential Learning Ability for a Reinforcement Learning Algorithm

Reinforcement learning (RL) algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, neural network function approximators suffer from a number of problems like learning becomes difficult when the training data are given sequentially, difficult to determine structural parameters, and usually result in local minima or overfitting. In this paper, a novel on-line sequential learning evolving neural network model design for RL is proposed. We explore the use of minimal resource allocation neural network (mRAN), and develop a mRAN function approximation approach to RL systems. Potential of this approach is demonstrated through a case study. The mean square error accuracy, computational cost, and robustness properties of this scheme are compared with static structure neural networks.