conftrace_

reward composition

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

ai-generated feedback (1) fairness theory (1) fair training (1) fair reward (1) language model (1) mirror descent (1) reinforcement learning from human feedback (1) reinforcement learning (1)

Papers

Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024