Poster · Sydney
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Ved Sriraman, Peihan Liu, Daniel Hsu, Adam Block
- Organisations
- Columbia University
- QRS classification
- Reinforcement learning, Language models