Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving

Abstract

Recent advances in Reinforcement Learning (RL) combined with Deep Learning (DL) have demonstrated impressive performance in complex tasks, including autonomous driving. The use of RL agents in autonomous driving leads to a smooth human-like driving experience, but the limited interpretability of Deep Reinforcement Learning (DRL) creates a verification and certification bottleneck. Instead of relying on RL agents to learn complex tasks, we propose HPRL - Hierarchical Program-triggered Reinforcement Learning, which uses a hierarchy consisting of a structured program along with multiple RL agents, each trained to perform a relatively simple task. The focus of verification shifts to the master program under simple guarantees from the RL agents, leading to a significantly more interpretable and verifiable implementation as compared to a complex RL agent. The evaluation of the framework is demonstrated on different driving tasks, and NHTSA precrash scenarios using CARLA, an open-source dynamic urban simulation environment.

arXiv commentThe paper is under consideration in Transactions on Intelligent Transportation Systems

References in corpus (6)

• End to End Learning for Self-Driving Cars
• Deep Reinforcement Learning framework for Autonomous Driving
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• On a Formal Model of Safe and Scalable Self-driving Cars
• Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
• Hierarchical Reinforcement Learning for Self-Driving Decision-Making without Reliance on Labeled Driving Data

Cited by in corpus (2)

• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation