Object Detection for Reinforcement Learning Agents

Abstract

In traditional reinforcement learning applications with images as input, the observation for the agent to learn from, is an image. In these models, a Convolutional Neural Network (CNN) is typically used to extract the features before for the learning process, in order to maximize the cumulative reward. In this paper, a different approach for pre-processing the input for reinforcement learning agents is considered. The proposed approach uses object detectors instead instead of CNNs, and converts each input image into bounding boxes and object locations for the agent to learn from.