Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration

TL;DR

This paper introduces GOLD, a framework that distills offline expert policies into lightweight models to improve safe reinforcement learning, especially in safety-critical real-world tasks like autonomous driving.

Contribution

GOLD is a novel offline-to-online safe RL framework that effectively distills offline decision transformer policies into lightweight models for real-time safety-critical applications.

Findings

GOLD outperforms offline and online safe RL methods in benchmarks.

GOLD successfully applies to real-world autonomous driving scenarios.

Distilled policies meet real-time inference requirements.

Abstract

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the overall performance. In many realistic tasks, e.g. autonomous driving, large-scale expert demonstration data are available. We argue that extracting expert policy from offline data to guide online exploration is a promising solution to mitigate the conserveness issue. Large-capacity models, e.g. decision transformers (DT), have been proven to be competent in offline policy learning. However, data collected in real-world scenarios rarely contain dangerous cases (e.g., collisions), which makes it prohibitive for the policies to learn safety concepts. Besides, these bulk policy networks cannot meet the computation speed requirements at inference time on real-world tasks such as autonomous driving. To this end, we propose Guided Online Distillation (GOLD), an offline-to-online safe RL framework. GOLD distills an offline DT policy into a lightweight policy network through guided online safe RL training, which outperforms both the offline DT policy and online safe RL algorithms. Experiments in both benchmark safe RL tasks and real-world driving tasks based on the Waymo Open Motion Dataset (WOMD) demonstrate that GOLD can successfully distill lightweight policies and solve decision-making problems in challenging safety-critical scenarios.