Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability

ArXi:2605.14246v1 Announce Type: new Many safety-critical control problems are modeled as risk-sensitive partially observable Marko decision processes, where the controller must make decisions from incomplete observations while balancing task performance against safety risk. Although belief-space planning provides a principled solution, maintaining and planning over beliefs can be computationally costly and sensitive to model specification in practical domains. We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.