方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 自监督强化学习× | 迁移学习与强化学习 (Transfer RL) 是一种训练范式，其中代理在一个或多个源任务中获得的知识× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2020 | 2009 (survey); concept from early 2000s |
| 提出者≠ | Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries) | Taylor, M. E. & Stone, P. |
| 类型≠ | Self-supervised auxiliary-task learning for RL | Transfer learning paradigm for sequential decision-making |
| 开创性文献≠ | 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 ↗ |
| 别名 | 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 |
| 相关 | 4 | 4 |
| 摘要≠ | 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. |
| ScholarGate数据集 ↗ |
|
|