Safety First, Reward Second — But Not Last
Opening — Why this matters now Reinforcement learning has spent the last decade mastering games, simulations, and neatly bounded optimization problems. Reality, inconveniently, is none of those things. In robotics, autonomous vehicles, industrial automation, and any domain where mistakes have real-world consequences, almost safe is simply unsafe. Yet most “safe RL” methods quietly rely on a compromise: allow some violations, average them out, and hope the system behaves. This paper refuses that bargain. It treats safety as a hard constraint, not a tunable preference—and then asks an uncomfortable question: can we still learn anything useful? ...