Poster · Sydney
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in Policy Optimization
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Yu Li, Rui Miao, Tian Lan, Zhengling Qi
- Organisations
- George Washington University, University of Texas at Dallas
- QRS classification
- Reinforcement learning, Probabilistic methods