SOURCE-LINKED INTELLIGENCE

Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields

arXiv · AI, language, vision and robotics · article · Oct 14, 2026 · UTC

Despite the Markov assumption, safety failures in robot reinforcement learning rarely occur instantaneously; they typically emerge over several steps as the policy enters unfamiliar states under disturbances and domain shift. We address this limitation by learning a receding-horizon safety critic that predicts whether a state will remain non-terminating over the next receding horizon, enabling anticipatory detection of impending locomotion failures. The critic is trained from rollout-derived horizon labels with a composite objective that combines horizon classification, control-barrier-functio

Read original source ↗ Open in workspace

recordType

paper

region

Global