方法对比

	微调强化学习	微调 BERT 分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2017–2022	2019
提出者	Christiano, P. et al.; Ouyang, L. et al.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI)
类型	Policy adaptation via fine-tuning	Pre-trained transformer fine-tuned for classification
开创性文献	Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
别名	RL fine-tuning, policy fine-tuning, RLHF, reinforcement learning from human feedback	BERT fine-tuning, BERT classifier, fine-tuned BERT, BERT sequence classification
相关	5	5
摘要	Fine-Tuned Reinforcement Learning adapts a pre-trained policy or model to a new task or behavioral objective using reinforcement signals — including human feedback — rather than retraining from scratch. Popularized by RLHF, it is the core technique behind aligning large language models and adapting deep RL agents to specialized environments with minimal additional data.	Fine-Tuned BERT-based Classification adapts a pre-trained BERT transformer to a specific text classification task by adding a lightweight output layer and continuing gradient-based training on labelled examples. It consistently achieves near-state-of-the-art accuracy on sentiment analysis, topic categorisation, intent detection, and other NLP classification tasks with relatively small labelled datasets.