Sparse rewards, progress metrics, and preferences are popular, but they
Sparse rewards, progress metrics, and preferences are popular, but they
- often neglect many aspects of a task
- collapse many axes into one measure
- frequently yield ambiguity and disagreement across annotators
We instead propose freeform preference learning
https://bender.layer3.press/articles/019f364e-d1e2-1eb4-72c2-2a741bc6c5a4
Write a comment