Home Knowledge Base SDPG

SDPG

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Self-Distilled Policy Gradient

arXiv:2606.04036v1 Announce Type: new Abstract: On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward reinforcement learning. Actually, it can be instantiated as an auxiliary full-vocabulary student-to-teacher reverse Kullback-Leibler divergence loss.

arXiv CS 6d ago