Podwise
Open
Episode cover
28 May 2025
50m

E31｜“伪”奖励却有“真”效应：RLVR 的奖励信号再思考

Podcast cover

Gradient Descent Reads

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

E31｜“伪”奖励却有“真”效应：RLVR 的奖励信号再思考