Sign in

Efficient RLHF: Reducing the Memory Usage of PPO.

Michael SantacroceYadong LuHan YuYuanzhi LiYelong Shen
Published in: CoRR (2023)
Keyphrases
  • memory usage
  • memory footprint
  • computationally expensive
  • memory requirements
  • database
  • artificial intelligence
  • information systems
  • neural network
  • machine learning
  • computer vision
  • similarity measure