From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning

Documenti analoghi

• Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
  di: Chen, Xinzhu, et al.
  Pubblicazione: (2026)
• LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
  di: Niu, Wenzhe, et al.
  Pubblicazione: (2025)
• UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning
  di: Zhang, Feng, et al.
  Pubblicazione: (2026)
• Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering
  di: Zhang, Nonghai, et al.
  Pubblicazione: (2026)
• Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
  di: Liu, Yan, et al.
  Pubblicazione: (2026)