#machine learning
May 2026
Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
Temperature-Scaled On-Policy Self-Distillation (TS-OPSD), a lightweight policy reheating method that internalizes the exploratory effect of temperature into model parameters, suggests that entropy restoration can serve as a simple post-collapse intervention for extending reasoning-oriented RL.
Xue Yang, Jiachen Yu, J. Wu et al.
· arXiv.org · 1 citation