Poster · Sydney
Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Aria Wong, Joshua Engels, Neel Nanda
- Organisations
- ML, Alignment Theory Scholars, Google DeepMind
- QRS classification
- Reinforcement learning