Skip to content
conftrace_

synthetic labeller

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

synthetic label (1) annotator agreement (1) inter-annotator agreement (1) preference-based reinforcement learning (1) policy training (1) human feedback (1) policy learning (1) deep reinforcement learning (1)

Papers

Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated AAAI 2024