Methoden vergelijken

	Semi-gesuperviseerd Reinforcement Learning	Zelfgesuperviseerd Reinforcement Learning
Vakgebied	Deep learning	Deep learning
Familie	Machine learning	Machine learning
Jaar van ontstaan	2020s	2020
Grondlegger	Multiple contributors (Laskin, Srinivas, Abbeel et al.)	Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries)
Type	Semi-supervised training paradigm for RL agents	Self-supervised auxiliary-task learning for RL
Oorspronkelijke bron	Zhan, X., Zhu, X., & Shi, H. (2022). Deepthermal: Combustion optimization for thermal power generating units using offline reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4680–4688.	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.
Aliassen	SSRL, semi-supervised RL, RL with unlabeled data, label-efficient reinforcement learning	SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL
Verwant	6	4
Samenvatting	Semi-supervised reinforcement learning (SSRL) combines standard reinforcement learning — where an agent learns from sparse reward signals — with semi-supervised techniques that extract structure from unlabeled environment interactions. The goal is to improve sample efficiency and generalization when reward feedback is costly, delayed, or available only for a fraction of the agent's experience.	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.