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