Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving

TL;DR

This paper introduces HPRL, a hierarchical framework combining structured programs with multiple simple RL agents to improve interpretability and verifiability in autonomous driving tasks.

Contribution

The paper proposes HPRL, a novel hierarchical approach that enhances interpretability and verification of RL-based autonomous driving systems by structuring tasks with a master program and simple RL agents.

Findings

HPRL improves interpretability over traditional RL methods.

The framework is effective in urban driving scenarios.

Verification is simplified through hierarchical structure.

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.