방법 비교

	자기 지도 강화 학습	자가 지도 합성곱 신경망
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2020	2018–2020
창시자	Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries)	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)
유형	Self-supervised auxiliary-task learning for RL	Self-supervised deep learning
원전	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.	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607.
별칭	SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN
관련	4	5
요약	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.	A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotated datasets while preserving the spatial feature-extraction strengths of convolutional architectures.