constrained markov decision process

4 papers

• Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
• Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
• Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning