Utilization of Deep Reinforcement Learning for saccadic-based object visual search

摘要

The paper focuses on the problem of learning saccades enabling visual objectsearch. The developed system combines reinforcement learning with a neuralnetwork for learning to predict the possible outcomes of its actions. Wevalidated the solution in three types of environment consisting of(pseudo)-randomly generated matrices of digits. The experimental verificationis followed by the discussion regarding elements required by systems mimickingthe fovea movement and possible further research directions.