Login / Signup

Safe RLHF: Safe Reinforcement Learning from Human Feedback.

Josef DaiXuehai PanRuiyang SunJiaming JiXinbo XuMickel LiuYizhou WangYaodong Yang
Published in: CoRR (2023)
Keyphrases
  • reinforcement learning
  • data mining
  • neural network
  • machine learning
  • artificial intelligence
  • e learning
  • state space
  • least squares
  • human interaction
  • action selection