방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자기 지도 강화 학습× | 강화학습× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2020 | 1950s–1998 |
| 창시자≠ | Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries) | Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations) |
| 유형≠ | Self-supervised auxiliary-task learning for RL | Sequential decision-making framework |
| 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. link ↗ | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 |
| 별칭 | SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL | RL, reward-based learning, trial-and-error learning, policy optimization |
| 관련≠ | 4 | 2 |
| 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. | Reinforcement Learning (RL) is a framework in which an agent learns to make sequential decisions by interacting with an environment, receiving scalar reward signals, and updating a policy to maximise cumulative future reward. Unlike supervised learning, no labeled examples are provided; the agent discovers optimal behavior entirely through experience and delayed feedback. |
| ScholarGate데이터셋 ↗ |
|
|