Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviors are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today’s common actor-critic architecture to a three-component learning framework, in which three neural networks are used to approximate the policy function, value function and a newly added risk function, respectively. Meanwhile, a trust region constraint is added to allow large update steps without breaking the monotonic improvement condition. To ensure the feasibility of safety constrained problems, synchronized parallel learners are employed to explore different state spaces, which accelerates learning and policy-update. The simulations of two scenarios for autonomous vehicles confirm we can ensure safety while achieving fast learning.
Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization*
2020-09-20
2798621 byte
Conference paper
Electronic Resource
English
Safe Reinforcement Learning with Policy-Guided Planning for Autonomous Driving
British Library Conference Proceedings | 2020
|Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA
ArXiv | 2023
|Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles
ArXiv | 2019
|Deep reinforcement‐learning‐based driving policy for autonomous road vehicles
Wiley | 2020
|Deep reinforcement-learning-based driving policy for autonomous road vehicles
IET | 2019
|