Tag: Token-Level Credit Assignment
All the articles with the tag "Token-Level Credit Assignment".
-
Learning Explainable Dense Reward Shapes via Bayesian Optimization
Published: at 04:30 PM
55.26 🤔本文提出一种通过Bayesian Optimization学习解释性密集奖励形状的方法，以解决RLHF中奖励稀疏问题，实现token级信用分配优化，提升训练效率和性能，同时保持最优政策不变。