Paper Title
An Automatic Object Detection Using Deep Q Learning and Yolox Network

Abstract
Automatic object detection in maritime environments is essential for applications such as navigation, environmental monitoring, and disaster management. This paper introduces a novel framework integrating Deep Q-Learning and the YOLOX network to detect objects such as ships, icebergs, and other maritime entities. YOLOX, a state-of-the-art object detection model, is employed to ensure high accuracy and speed, while Deep Q-Learning optimizes detection parameters dynamically to enhance performance in challenging scenarios like varying weather conditions and occlusions. Experimental results on maritime datasets demonstrate the proposed system's capability to accurately and efficiently detect objects, showcasing its potential for real-world maritime applications. Keywords - Object Detection, YOLOX, Deep Q Learning, Marine Environment, Autonomous Navigation, Real-time Detection, Marine Surveillance