From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

Documenti analoghi

• Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
  di: Cen, Zhepeng, et al.
  Pubblicazione: (2024)
• Offline Learning and Forgetting for Reasoning with Large Language Models
  di: Ni, Tianwei, et al.
  Pubblicazione: (2025)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
  di: Yang, Ke, et al.
  Pubblicazione: (2024)
• Budgeting Counterfactual for Offline RL
  di: Liu, Yao, et al.
  Pubblicazione: (2023)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
  di: Zeng, Siliang, et al.
  Pubblicazione: (2023)