Utilization of Deep Reinforcement Learning for saccadic-based object visual search
arXiv:1610.06492
Abstract
The paper focuses on the problem of learning saccades enabling visual object search. The developed system combines reinforcement learning with a neural network for learning to predict the possible outcomes of its actions. We validated the solution in three types of environment consisting of (pseudo)-randomly generated matrices of digits. The experimental verification is followed by the discussion regarding elements required by systems mimicking the fovea movement and possible further research directions.
Paper submitted to special session on Machine Intelligence organized during 23rd International AUTOMATION Conference