RowitZou / topic-dialog-summ

AAAI-2021 paper: Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling.
MIT License
77 stars 9 forks source link

RLLOSS #24

Closed lulia0228 closed 2 years ago

lulia0228 commented 2 years ago

还未深入看rl梯度策略,想请教下作者我的rlloss是否正常 image

RowitZou commented 2 years ago

RL loss是正常的,正负分别代表相对于baseline更好和更差的采样结果。

lulia0228 commented 2 years ago

RL loss是正常的,正负分别代表相对于baseline更好和更差的采样结果。

感谢您的回复!