RL Starts before RL: On Policy Distillation for Better Reinforcement Learning

2026-09-23

AI Summary

研究通过使用在线策略蒸馏（OPD）作为强化学习（RL）的准备阶段，提高RL最终性能的问题。探讨了不同蒸馏方法对后续RL效果的影响。

Abstract

Reinforcement learning (RL) improves reasoning, but its performance depends on the policy from which training begins. We study on-policy distillation (OPD) as a preparation stage for RL and ask whether its benefits extend beyond improvements in the distilled model's initial accuracy. Under shared RL settings, students initialized with OPD reach higher final performance than those trained with direct RL or supervised fine-tuning followed by RL. This advantage can emerge even when OPD produces little immediate improvement in accuracy. Pre-RL Pass@k does not fully explain the benefit: similar or even higher values do not necessarily lead to better performance after RL. Behavioral analyses point to alignment with the teacher's distribution beyond top-1 agreement as a possible explanation. Such alignment may favor higher-quality reasoning paths while retaining alternatives that RL can further refine using outcome feedback. We further examine how trajectory sources and divergence objectives affect the value of distillation for subsequent RL. Standard reverse-KL OPD performs better before RL, but forward-KL OPD overtakes it afterward; with teacher-generated distillation trajectories, reverse KL remains ahead at both stages. These findings suggest that the preferred distillation objective depends on both the trajectory source and the training that follows. Our results support evaluating OPD as preparation for RL and selecting distillation choices by the performance achieved after subsequent training.

Problem

• Reinforcement Learning
• Policy Distillation
• Training Initialization

Innovation

• on-policy distillation
• reinforcement learning
• performance improvement
• teacher's distribution alignment
• divergence objectives