AUTONOMOUS VEHICLE SIMULATION USING REINFORCEMENT LEARNING

Abstract

onments. RL is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. And this project emphasizes on autonomous driving via Reinforcement Learning. Unlike other types of learning like Supervised and Unsupervised Learning, this type of learning learns through hit and trial with penalty approach. And with deep learning, it optimizes its neural network for better decision making. So, it is called Deep Reinforcement Learning. Among these Deep Reinforcement Learning, Deep Q Learning (DQN) is one of the approach which leverages on Q value generated by the neural network. This concept of neural network eliminates the tedious task of managing tables used in traditional Reinforcement Learning Algorithms. Using those Deep Reinforcement Algorithms, not only it can be applied on autonomous driving but in many other field like in robotics.