Deep Reinforcement and Imitation Learning for Autonomous Driving: A Systematic Review in the CARLA Simulation Environment

Autonomous driving is a complex and fast-evolving domain at the intersection of robotics, machine learning, and control systems. This paper provides a systematic review of recent developments in reinforcement learning (RL) and imitation learning (IL) approaches for autonomous vehicle control in the CARLA simulator. We analyze RL-based and IL-based studies, extracting and comparing their formulations of state, action, and reward spaces. Special attention is given to the design of reward functions, control architectures, and integration pipelines. Comparative graphs and diagrams illustrate performance trade-offs. We further highlight gaps in generalization to real-world driving scenarios, robustness under dynamic environments, and scalability of agent architectures. Finally, we discuss hybrid paradigms that integrate IL and RL, such as Generative Adversarial Imitation Learning (GAIL), and propose future research directions. This review aims to support researchers in understanding prevailing trends and informed model development for simulated autonomous driving tasks.