Poster · Sydney
DeFlow: Decoupling Behavior-Prior Modeling and Value Maximization for Offline Policy Extraction
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Zhancun Mu, Chi Zhang
- Organisations
- Peking University, University of California, Los Angeles
- QRS classification
- Reinforcement learning