2026
DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes
IJCAI 2026
Reinforcement learning (RL) policies often outperform classical controllers in simulation, yet rarely reach production in safety-critical processes. The barrier is that there is no principled way to answer “Is this policy safe to deploy?” with statistical guarantees. We introduce DEPLOY-RL, a post-t