Query-Policy Misalignment in Preference-Based Reinforcement Learning

Documenti analoghi

• CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
  di: Mu, Ni, et al.
  Pubblicazione: (2025)
• STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
  di: Luan, Yao, et al.
  Pubblicazione: (2025)
• Feasible Policy Iteration for Safe Reinforcement Learning
  di: Yang, Yujie, et al.
  Pubblicazione: (2023)
• Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies
  di: Luo, Yu, et al.
  Pubblicazione: (2024)
• Preference-based Multi-Objective Reinforcement Learning
  di: Mu, Ni, et al.
  Pubblicazione: (2025)