Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone

Documenti analoghi

• Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
  di: Nakamoto, Mitsuhiko, et al.
  Pubblicazione: (2023)
• Is Value Learning Really the Main Bottleneck in Offline RL?
  di: Park, Seohong, et al.
  Pubblicazione: (2024)
• Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
  di: Xiao, Wei, et al.
  Pubblicazione: (2025)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
  di: Tajwar, Fahim, et al.
  Pubblicazione: (2024)
• Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
  di: Zhou, Runlong, et al.
  Pubblicazione: (2024)