Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations

Documenti analoghi

• Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
  di: Kong, Lingkai, et al.
  Pubblicazione: (2025)
• On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
  di: Wang, Tonghan, et al.
  Pubblicazione: (2024)
• LLM Active Alignment: A Nash Equilibrium Perspective
  di: Wang, Tonghan, et al.
  Pubblicazione: (2026)
• VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping
  di: Xiong, Guojun, et al.
  Pubblicazione: (2025)
• Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness
  di: Parthasarathy, Ambreesh, et al.
  Pubblicazione: (2025)