arXiv:2606.22600v3 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers. In the standard KL objective of OPD, token-level losses are uniformly averaged, implying equal weights for all tokens. However, we discover that not…
Thank you for reading this post, don't forget to subscribe!
Source: cs.AI updates on arXiv.org
Automatically aggregated summary — full article and all rights belong to the original publisher.