#machine learning
Oct 2024
Dual Active Learning for Reinforcement Learning from Human Feedback
This paper first proposes a dual active reward learning algorithm for the simultaneous selection of conversations and teachers, and applies pessimistic RL to solve the alignment problem, based on the learned reward estimator.
Pang-Pang Liu, Cheng-Chun Shi, W. Sun
· arXiv.org · 28 citations
· ⚡2