Constrained Policy Optimization Algorithm for Autonomous Driving via Reinforcement Learning

Reinforcement Learning (RL) has achieved great success in many complicated and difficult problems in recent years. In the field of autonomous driving, RL promises to make road transportation safer, more efficient and more sustainable through intelligent sensing, decision and control techniques in driving tasks. Due to above reasons it is expected that RL will provide a huge role in autonomous driving as well. In this paper, we present the methodology of constrained policy optimization and Markov modeling. In order to ensure the learning process, this paper chooses to explore an algorithm called the constrained policy optimization (CPO) followed by trust region policy optimization and Markov modeling. CPO algorithm ensures the policy by modifying the policy update. In order to fully verify the learning function of the CPO algorithm, many test fields are selected from straight road to slightly complex geometry.