Poster · Sydney
Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
- 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
- Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae, Junmo Kim
- Organisations
- KAIST
- QRS classification
- Reinforcement learning