Meta-Learning Objectives for Preference Optimization

Documenti analoghi

• The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
  di: Sims, Anya, et al.
  Pubblicazione: (2024)
• EvIL: Evolution Strategies for Generalisable Imitation Learning
  di: Sapora, Silvia, et al.
  Pubblicazione: (2024)
• Learning mirror maps in policy mirror descent
  di: Alfano, Carlo, et al.
  Pubblicazione: (2024)
• SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
  di: Zheng, Zhi, et al.
  Pubblicazione: (2025)
• Incorporating Unlabelled Data into Bayesian Neural Networks
  di: Sharma, Mrinank, et al.
  Pubblicazione: (2023)