Porovnat metody

	Jemně doladěné zpatňovací učení	Samoučící se zpatňovací učení
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2017–2022	2020
Tvůrce	Christiano, P. et al.; Ouyang, L. et al.	Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries)
Typ	Policy adaptation via fine-tuning	Self-supervised auxiliary-task learning for RL
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.	Laskin, M., Srinivas, A., & Abbeel, P. (2020). CURL: Contrastive Unsupervised Representations for Reinforcement Learning. Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 5639–5650.
Další názvy	RL fine-tuning, policy fine-tuning, RLHF, reinforcement learning from human feedback	SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task 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.	Self-supervised Reinforcement Learning (SSL-RL) augments standard RL training with self-supervised auxiliary objectives — such as contrastive, predictive, or data-augmentation-based tasks — applied to the agent's own experience. These objectives improve the quality of learned representations without requiring extra human labels, enabling faster convergence and better sample efficiency, especially in high-dimensional observation spaces like raw pixels.