Since deep neural networks' resurgence, reinforcement learning has gradually strengthened and surpassed humans in many conventional games. However, it is not easy to copy these accomplishments to autonomous driving because state spaces are immensely complicated in the real world and action spaces are continuous and fine control is necessary. Besides, autonomous driving systems must also maintain their functionality regardless of the environment's complexity. The deep reinforcement learning domain (DRL) has become a robust learning framework to handle complex policies in high dimensional surroundings with deep representation learning. This research outlines deep, reinforcement learning algorithms (DRL). It presents a nomenclature of autonomous driving in which DRL techniques have been used, thus discussing important computational issues in evaluating autonomous driving agents in the real environment. Instead, it involves similar but not standard RL techniques, adjoining fields such as emulation of actions, modelling imitation, inverse reinforcement learning. The simulators' role in training agents is addressed, as are the methods for validating, checking and robustness of existing RL solutions.

翻译：自深度神经网络复兴以来，强化学习已在众多传统博弈中逐步增强并超越人类表现。然而，将这些成就复制到自动驾驶领域并非易事，因为现实世界中的状态空间极其复杂，动作空间具有连续性且需要精确控制。此外，自动驾驶系统无论环境如何复杂，都必须维持其功能完整性。深度强化学习领域已成为一个稳健的学习框架，能够通过深度表征学习处理高维环境中的复杂策略。本研究概述了深度强化学习算法，并构建了应用DRL技术的自动驾驶术语体系，进而探讨了在真实环境中评估自动驾驶智能体的重要计算问题。同时涉及与之相似但非标准的强化学习技术，包括动作仿真、模仿学习和逆向强化学习等相邻领域。本文论述了模拟器在智能体训练中的作用，以及现有强化学习解决方案的验证、检查与鲁棒性方法。