Understanding the performance gap between online and offline alignment algorithms

Documenti analoghi

• Generalized Preference Optimization: A Unified Approach to Offline Alignment
  di: Tang, Yunhao, et al.
  Pubblicazione: (2024)
• Off-policy Distributional Q($λ$): Distributional RL without Importance Sampling
  di: Tang, Yunhao, et al.
  Pubblicazione: (2024)
• Large-scale semi-supervised learning with online spectral graph sparsification
  di: Calandriello, Daniele, et al.
  Pubblicazione: (2026)
• VA-learning as a more efficient alternative to Q-learning
  di: Tang, Yunhao, et al.
  Pubblicazione: (2023)
• RL-finetuning LLMs from on- and off-policy data with a single algorithm
  di: Tang, Yunhao, et al.
  Pubblicazione: (2025)