State-wise Safe Reinforcement Learning: A Survey

TL;DR

This survey reviews methods for enforcing state-wise safety constraints in reinforcement learning, crucial for real-world applications like autonomous driving and robotics, highlighting current approaches, limitations, and future directions.

Contribution

It provides a comprehensive overview of state-wise constrained RL, analyzing safety guarantees, scalability, and performance trade-offs within the SCMDP framework.

Findings

Existing methods vary in safety guarantees and scalability.

Trade-offs between safety and reward performance are identified.

Current approaches have limitations in safety during training and convergence.

Abstract

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction. State-wise constraints are one of the most common constraints in real-world applications and one of the most challenging constraints in Safe RL. Enforcing state-wise constraints is necessary and essential to many challenging tasks such as autonomous driving, robot manipulation. This paper provides a comprehensive review of existing approaches that address state-wise constraints in RL. Under the framework of State-wise Constrained Markov Decision Process (SCMDP), we will discuss the connections, differences, and trade-offs of existing approaches in terms of (i) safety guarantee and scalability, (ii) safety and reward performance, and (iii) safety after convergence and during training. We also summarize limitations of current methods and discuss potential future directions.