Conformal Policy Control

arXiv:2603.02196v2 Announce Type: replace-cross Abstract: An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but excessive conservatism discourages exploration. How much behavior change is too much? We show how to use any safe reference policy as a probabilistic regulator for any optimized but untested policy. Conformal calibration on data from the safe policy determines how aggressively the new policy can act, while provably enforcing the user's declared risk tolerance. Unlike conservative optimization methods, we do not assume the user has identified the correct model class nor tuned any hyperparameters. Unlike previous conformal methods, our theory provides finite-sample guarantees even for non-monotonic bounded loss functions. Our experiments on applications ranging from natural language question answering to biomolecular engineering show that safe exploration is not only possible from the first moment of deployment, but can also improve performance.

Related

• Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees
• Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?
• Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design
• Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
• A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance

Source: arXiv cs.LG | 2026-04-17