2 papers
cs.LG2026
BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control
Yifan Zhang, Liang Zheng
Real-world control systems frequently operate under \emph{piecewise stationary} conditions, where dynamics remain stable for extended periods before undergoing abrupt regime change…
cs.LG2026
RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approach
Yifan Zhang, Liang Zheng
Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard actor-critic algorithms suffer fr…