Improving Generalization of Alignment with Human Preferences through Group Invariant Learning.
Rui ZhengWei ShenYuan HuaWenbin LaiShihan DouYuhao ZhouZhiheng XiXiao WangHaoran HuangTao GuiQi ZhangXuanjing HuangPublished in: CoRR (2023)
Keyphrases
- learning process
- learning systems
- learning algorithm
- knowledge acquisition
- prior knowledge
- online learning
- explanation based generalization
- human learning
- learning tasks
- artificial intelligence
- neural network
- reinforcement learning
- unsupervised learning
- training data
- decision making
- learning analytics
- cooperative learning
- preference learning
- machine learning