Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

Documenti analoghi

• Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
  di: Zhang, Xiaoyun, et al.
  Pubblicazione: (2025)
• Explainable Reinforcement Learning via a Causal World Model
  di: Yu, Zhongwei, et al.
  Pubblicazione: (2023)
• PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
  di: Jian, Ai, et al.
  Pubblicazione: (2025)
• TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
  di: Jian, Ai, et al.
  Pubblicazione: (2026)
• Learning Causal Dynamics Models in Object-Oriented Environments
  di: Yu, Zhongwei, et al.
  Pubblicazione: (2024)