How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis

Documenti analoghi

• Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
  di: Takakura, Shokichi, et al.
  Pubblicazione: (2026)
• A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
  di: Wachi, Akifumi, et al.
  Pubblicazione: (2026)
• Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
  di: Takakura, Shokichi, et al.
  Pubblicazione: (2024)
• Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
  di: Takakura, Shokichi, et al.
  Pubblicazione: (2023)
• A Provable Approach for End-to-End Safe Reinforcement Learning
  di: Wachi, Akifumi, et al.
  Pubblicazione: (2025)