SafeReinfor-cement2026Safe Reinforcement Learning with Preference-based Constraint InferenceCheng-Lin Li, Guangchun Ruan, Hua GengarXiv.orgDOI
TiltedQuantileGradient2025Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement LearningCheng-Lin Li, Guangchun Ruan, Hua GengAAAI Conference on Artificial IntelligenceDOI