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