Lyapunov-based uncertainty-aware safe reinforcement learning

TL;DR

This paper introduces a Lyapunov-based, uncertainty-aware safe reinforcement learning framework that enhances safety and performance in complex, partially observable environments by integrating trajectory constraints, uncertainty quantification, and memory mechanisms.

Contribution

It proposes a novel Lyapunov-based model with uncertainty quantification and Transformer memory to improve safety and optimality in safe RL, especially in out-of-distribution scenarios.

Findings

Significant safety improvements in grid-world navigation tasks.

Enhanced performance in both fully and partially observable environments.

Effective identification of risk-averse actions through uncertainty estimation.

Abstract

Reinforcement learning (RL) has shown a promising performance in learning optimal policies for a variety of sequential decision-making tasks. However, in many real-world RL problems, besides optimizing the main objectives, the agent is expected to satisfy a certain level of safety (e.g., avoiding collisions in autonomous driving). While RL problems are commonly formalized as Markov decision processes (MDPs), safety constraints are incorporated via constrained Markov decision processes (CMDPs). Although recent advances in safe RL have enabled learning safe policies in CMDPs, these safety requirements should be satisfied during both training and in the deployment process. Furthermore, it is shown that in memory-based and partially observable environments, these methods fail to maintain safety over unseen out-of-distribution observations. To address these limitations, we propose a Lyapunov-based uncertainty-aware safe RL model. The introduced model adopts a Lyapunov function that converts trajectory-based constraints to a set of local linear constraints. Furthermore, to ensure the safety of the agent in highly uncertain environments, an uncertainty quantification method is developed that enables identifying risk-averse actions through estimating the probability of constraint violations. Moreover, a Transformers model is integrated to provide the agent with memory to process long time horizons of information via the self-attention mechanism. The proposed model is evaluated in grid-world navigation tasks where safety is defined as avoiding static and dynamic obstacles in fully and partially observable environments. The results of these experiments show a significant improvement in the performance of the agent both in achieving optimality and satisfying safety constraints.