AI RESEARCH
BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control
arXiv CS.LG
•
ArXi:2605.16170v1 Announce Type: new Real-world control systems frequently operate under \emph{piecewise stationary} conditions, where dynamics remain stable for extended periods before undergoing abrupt regime changes. Standard robust RL methods face a fundamental dilemma: a globally conservative policy wastes performance during stable periods, while a locally adaptive policy risks catastrophic failure when the regime changes undetected. We propose \textbf{BAPR} (Bayesian Amnesic Piecewise-Robust SAC), which unifies Bayesian Online Change Detection (BOCD) with robust ensemble RL.