Porovnat metody

	Jemně doladěné zpatňovací učení	Přenosové učení s učením posilováním
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2017–2022	2009 (survey); concept from early 2000s
Tvůrce	Christiano, P. et al.; Ouyang, L. et al.	Taylor, M. E. & Stone, P.
Typ	Policy adaptation via fine-tuning	Transfer learning paradigm for sequential decision-making
Původní zdroj	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.	Taylor, M. E., & Stone, P. (2009). Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research, 10, 1633–1685.
Další názvy	RL fine-tuning, policy fine-tuning, RLHF, reinforcement learning from human feedback	Transfer RL, TL for RL, cross-task reinforcement learning, inductive transfer in RL
Příbuzné	5	4
Shrnutí	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.	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.