Poster · Sydney
How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
- 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
- Rei Higuchi, Ryotaro Kawata, Akifumi Wachi, Shokichi Takakura, Kohei Miyaguchi, Taiji Suzuki
- Organisations
- University of Tokyo, LY Corp, LY Corporation
- QRS classification
- Reinforcement learning