State-Wise Safe Reinforcement Learning With Pixel Observations

TL;DR

This paper introduces a novel safe reinforcement learning algorithm that uses pixel observations and latent barrier functions to effectively balance safety and reward maximization, especially in complex environments.

Contribution

It proposes a new pixel-based safe RL method with a latent barrier-like function, enabling efficient safety constraint encoding and improved safety during training.

Findings

Significantly reduces safety violations during training

Achieves faster safety convergence than existing methods

Maintains competitive reward performance

Abstract

In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent must avoid unsafe regions without prior knowledge, adds another layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that efficiently encodes state-wise safety constraints with unknown hazard regions through a newly introduced latent barrier-like function learning mechanism. As a joint learning framework, our approach begins by constructing a latent dynamics model with low-dimensional latent spaces derived from pixel observations. We then build and learn a latent barrier-like function on top of the latent dynamics and conduct policy optimization simultaneously, thereby improving both safety and the total expected return. Experimental evaluations on the safety-gym benchmark suite demonstrate that our proposed method significantly reduces safety violations throughout the training process, and demonstrates faster safety convergence compared to existing methods while achieving competitive results in reward return.