方法对比

	迁移学习与强化学习 (Transfer RL) 是一种训练范式，其中代理在一个或多个源任务中获得的知识	微调强化学习
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2009 (survey); concept from early 2000s	2017–2022
提出者	Taylor, M. E. & Stone, P.	Christiano, P. et al.; Ouyang, L. et al.
类型	Transfer learning paradigm for sequential decision-making	Policy adaptation via fine-tuning
开创性文献	Taylor, M. E., & Stone, P. (2009). Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research, 10, 1633–1685.	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.
别名	Transfer RL, TL for RL, cross-task reinforcement learning, inductive transfer in RL	RL fine-tuning, policy fine-tuning, RLHF, reinforcement learning from human feedback
相关	4	5
摘要	Transfer Learning with Reinforcement Learning (Transfer RL) is a training paradigm in which knowledge acquired by an agent in one or more source tasks — encoded as policy weights, value functions, or learned representations — is reused to accelerate or improve learning in a related but different target task. It directly addresses the sample-inefficiency that plagues reinforcement learning from scratch in complex or expensive environments.	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.