kl regularization

5 papers

• Improving Video Generation with Human Feedback
• Last Iterate Convergence in Monotone Mean Field Games
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
• Preference Learning with Lie Detectors can Induce Honesty or Evasion
• Reinforcement Learning Finetunes Small Subnetworks in Large Language Models