Uporedite metode

	Polunadzirano učenje potkrepljivanjem	Samostalno nadgledano pojačano učenje
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2020s	2020
Tvorac	Multiple contributors (Laskin, Srinivas, Abbeel et al.)	Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries)
Tip	Semi-supervised training paradigm for RL agents	Self-supervised auxiliary-task learning for RL
Temeljni izvor	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.
Drugi nazivi	SSRL, semi-supervised RL, RL with unlabeled data, label-efficient reinforcement learning	SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL
Srodne	6	4
Sažetak	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.