通过变分学习进行RLVR的参数探索
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Carlsen Daheim, Iryna Gurevych
AI 速读 基于摘要
提出扰动参数策略优化（3PO）方法族，从参数后验采样不同策略以实现参数空间探索，并在数学推理与代码生成任务上报告优于GRPO的平均下游性能。
cs.LG · cs.AI · cs.CL
查看原文摘要
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcement learning recipes that can significantly impact downstream performance. Many existing methods control exploration in the action-space, for example, using temperature scaling. However, these methods cannot reorder tokens but only influence the variance in the output distribution. This limits exploration and can lead to divergence or stalled training. Here, we investigate parameter-space exploration, where rollouts are generated by sampling different policies from a posterior that may each explore different rollouts. Sampling less or more diverse policies is then a complementary control lever over exploration. We introduce a family of methods called Perturbed Parameter Policy Optimization (3PO) which use different sampling strategies and different rollout grouping for reward estimation. Experiments on Olmo-3-1025-7B and Qwen2.5-Math-7B across mathematical reasoning and code generation tasks show that these approaches can improve the average downstream performance over standard GRPO at a near-identical FLOPs cost. Moreover, using multiple parameter samples generally produces fewer zero-advantage groups and malformed or incorrect rollouts during training than GRPO and action-space baselines. Overall, our work presents evidence that parameter-space exploration can improve reinforcement learning for LLMs.