摘要:
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL(增强学习,针对小样本鲁棒性场景) NIPS-2020 abstract:reinforcement learning 在一些复杂任务场景 阅读全文
摘要:
最近在看Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces这篇文章时发现文章采用了一个R@k的评价指标来衡量模型的好坏。文章中提到了一句话“R@k is preferred for few- and zero 阅读全文