A1310
Title: Recent advances in reward modeling for reinforcement learning
Authors: Masashi Sugiyama - RIKEN/The University of Tokyo (Japan) [presenting]
Abstract: Reinforcement learning (RL) has achieved remarkable success in robotics, games, and language model post-training, where reward signals are essential for effective agent training. Recent research on advanced reward modeling will be presented. This includes robustifying RL through transfer and weakly supervised learning, coping with interval-based rewards, and exploring diverse reward aggregation frameworks that move beyond the traditional discounted sum.
