返回首页
RadarAI··论文与技术

ExploreNet:扩散GRPO的可学习探索

中文摘要

ExploreNet提出扩散GRPO可学习探索策略,通过引导模型自主发现更优解,显著提升强化学习推理表现。

English Summary

ExploreNet introduces a learnable exploration strategy for Diffusion GRPO, enabling models to autonomously discover better solutions and significantly enhance reasoning performance in reinforcement learning.

原文节选

推荐阅读! ExploreNet: Learning Where to Explore in Diffusion GRPO