Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
Johannes Ackermann, Takashi Ishida, Masashi Sugiyama
Reinforcement Learning from Human Feedback (RLHF) allows us to train models, such as language models (LMs), to follow complex human preferences. In RLHF for LMs, we first train an…
cs.LG2025
Recursive Reward Aggregation
Yuting Tang, Yivan Zhang, Johannes Ackermann +3
In reinforcement learning (RL), aligning agent behavior with specific objectives typically requires careful design of the reward function, which can be challenging when the desired…