Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment

Ähnliche Einträge

• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
  von: Li, Jiaxiang, et al.
  Veröffentlicht: (2024)
• Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots
  von: Dennler, Nathaniel, et al.
  Veröffentlicht: (2024)
• Quantifying Demonstration Quality for Robot Learning and Generalization
  von: Sakr, Maram, et al.
  Veröffentlicht: (2022)
• Inference of Human-derived Specifications of Object Placement via Demonstration
  von: Cuellar, Alex, et al.
  Veröffentlicht: (2025)
• Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration
  von: Sakr, Maram, et al.
  Veröffentlicht: (2024)