방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자기 지도 강화 학습× | 강화학습에서의 전이 학습× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2020 | 2009 (survey); concept from early 2000s |
| 창시자≠ | Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries) | Taylor, M. E. & Stone, P. |
| 유형≠ | Self-supervised auxiliary-task learning for RL | Transfer learning paradigm for sequential decision-making |
| 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 ↗ | Taylor, M. E., & Stone, P. (2009). Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research, 10, 1633–1685. link ↗ |
| 별칭 | SSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL | Transfer RL, TL for RL, cross-task reinforcement learning, inductive transfer in RL |
| 관련 | 4 | 4 |
| 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. | Transfer Learning with Reinforcement Learning (Transfer RL) is a training paradigm in which knowledge acquired by an agent in one or more source tasks — encoded as policy weights, value functions, or learned representations — is reused to accelerate or improve learning in a related but different target task. It directly addresses the sample-inefficiency that plagues reinforcement learning from scratch in complex or expensive environments. |
| ScholarGate데이터셋 ↗ |
|
|