Reinforcement learning in multiresolution object recognition

In this work, we propose an adaptive automatic target recognition (ATR) technique that exploits reinforcement learning (RL) for multiresolution object recognition. The RL structure is the implementation of neuro-dynamic programming (NDP) for the critic and action networks. The critic network calculates the cost-to-go function J* based on a simplistic ATR plant that involves multiresolution images as the input state variable. The calculation of this function, J* includes the role of the reinforcement signal in the critic network. Output of this critic stage is fed back to update the weights of both action and critic networks respectively. Our simulation results suggest that RL may be successfully integrated into an adaptive multiresolution ATR framework.