Skip to content
conftrace_

preference-based reward learning

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reward misidentification (1) causal confusion (1) spurious correlation (1) reward hacking (1) out-of-distribution generalization (1)

Papers

Causal Confusion and Reward Misidentification in Preference-Based Reward Learning ICLR 2023