# MInTRL: Off-policy Intervention can boost On-policy RL > Source: > Published: 2026-09-15 08:00:08+00:00 Reinforcement learning with verifiable rewards is typically performed on-policy, keeping training data close to the current policy but limiting learning to trajectories that the policy can discover itself. Off-policy methods such as supervised fine-tuning, on the other hand, can leverage external kn