Lignende værker

• Soft Policy Optimization: Online Off-Policy RL for Sequence Models
  af: Cohen, Taco, et al.
  Udgivet: (2025)
• Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data
  af: Tang, Yunhao, et al.
  Udgivet: (2025)
• On a few pitfalls in KL divergence gradient estimation for RL
  af: Tang, Yunhao, et al.
  Udgivet: (2025)
• Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
  af: Rowland, Mark, et al.
  Udgivet: (2024)
• VA-learning as a more efficient alternative to Q-learning
  af: Tang, Yunhao, et al.
  Udgivet: (2023)