AI RESEARCH

Safe Continual Reinforcement Learning in Non-stationary Environments

arXiv CS.LG

ArXi:2604.19737v1 Announce Type: new Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynamics and operating conditions can change unexpectedly.