Login / Signup

Provably Sample Efficient RLHF via Active Preference Optimization.

Nirjhar DasSouradip ChakrabortyAldo PacchianoSayak Ray Chowdhury
Published in: CoRR (2024)
Keyphrases
  • computationally efficient
  • optimization algorithm
  • cost effective
  • multi objective
  • sample size
  • efficient optimization