Reinforcement Learning by Guided Safe Exploration

TL;DR

This paper introduces a method for safe exploration in reinforcement learning by training a guide in a controlled environment to ensure safety, which then helps the target policy learn efficiently once the reward is revealed.

Contribution

It proposes a novel constrained reward-free RL framework that leverages a safety guide for secure exploration and transfer learning to improve target task performance.

Findings

The method enables safe transfer learning in RL.

It accelerates target task learning while maintaining safety.

Empirical results demonstrate improved safety and efficiency.

Abstract

Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once the reward is revealed. We consider the constrained reward-free setting, where an agent (the guide) learns to explore safely without the reward signal. This agent is trained in a controlled environment, which allows unsafe interactions and still provides the safety signal. After the target task is revealed, safety violations are not allowed anymore. Thus, the guide is leveraged to compose a safe behaviour policy. Drawing from transfer learning, we also regularize a target policy (the student) towards the guide while the student is unreliable and gradually eliminate the influence of the guide as training progresses. The empirical analysis shows that this method can achieve safe transfer learning and helps the student solve the target task faster.