arXiv cs.AI / cs.LG / cs.CL·8d agoFAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems#safe-rl#humanoid#safety-filterAI research 2 sources1
arXiv cs.AI / cs.LG / cs.CL·8d agoA Unified Bellman Operator for Safety-Critical Reinforcement Learning#reinforcement-learning#safe-rl#bellman-operatorAI research
arXiv cs.AI / cs.LG / cs.CL·Sep 14, 2026Safe Meta-Reinforcement Learning via Information Space Reachability#adaptive-agents#bellman-equation#constrained-policyAI research