Context-aware Safe Reinforcement Learning For Non-stationary Environments

Abstract

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety constraints. However, few studies have addressed the non-stationary disturbances in the environments, which may cause catastrophic outcomes. In this paper, we propose the context-aware safe reinforcement learning (CASRL) method, a meta-learning framework to realize safe adaptation in non-stationary environments. We use a probabilistic latent variable model to achieve fast inference of the posterior environment transition distribution given the context data. Safety constraints are then evaluated with uncertainty-aware trajectory sampling. The high cost of safety violations leads to the rareness of unsafe records in the dataset. We address this issue by enabling prioritized sampling during model training and formulating prior safety constraints with domain

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keychen2021context

Related papers

• Safe Continual Reinforcement Learning In Non-stationary Environments (2026)12.89
• Safe In-context Reinforcement Learning (2025)0.00
• Actsafe: Active Exploration With Safety Constraints For Reinforcement Learning (2024)0.00
• Safe Continual Reinforcement Learning Methods For Nonstationary Environments. Towards A Survey Of The State Of The Art (2026)0.00
• Concurrent Learning Of Policy And Unknown Safety Constraints In Reinforcement Learning (2024)0.00
• Conservative And Adaptive Penalty For Model-based Safe Reinforcement Learning (2021)0.00
• Safety Aware Reinforcement Learning (SARL) (2020)0.00
• Online Reinforcement Learning In Non-stationary Context-driven Environments (2023)0.00