Poster · Sydney
Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Mingyi Li, Taira Tsuchiya, Kenji Yamanishi
- Organisations
- University of Tokyo
- QRS classification
- Reinforcement learning, Learning theory, Representation and transfer learning