Safety controllers stop chasing average reward: training on the weakest certificate margin yields zero test violations in three domains
Learned controllers for safety-critical systems usually maximize average reward first and add safety through penalties, constraints or runtime filters. CeDL instead trains without reward: it combines Lyapunov stability, control-barrier safety, temporal-logic robustness and feasibility margins into one certificate margin, and an adversarial falsifier repeatedly surfaces the scenarios closest to violation. Across simulated URLLC wireless resource allocation, energy-safe sensor-network routing and robotic obstacle avoidance, CeDL reports zero observed test-set violations and larger minimum certificate margins than reward-based RL, constrained RL, model predictive control, shielded RL and classical controllers.