EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

Documenti analoghi

• Debiased Model-based Representations for Sample-efficient Continuous Control
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2026)
• Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
  di: Chen, Yangkun, et al.
  Pubblicazione: (2024)
• Cross-Domain Offline Policy Adaptation via Selective Transition Correction
  di: Yan, Mengbei, et al.
  Pubblicazione: (2026)
• Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
  di: Xu, Xin, et al.
  Pubblicazione: (2026)
• Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
  di: Qu, Yun, et al.
  Pubblicazione: (2026)