Machine learningDeep learning / NLP / CV
半监督强化学习
半监督强化学习（SSRL）结合了标准的强化学习——即智能体从稀疏奖励信号中学习——以及从无标签的环境交互中提取结构的半监督技术。其目标是在奖励反馈成本高昂、延迟或仅对智能体经验的一小部分可用时，提高样本效率和泛化能力。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- 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. link ↗
- 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 ↗
如何引用本页
ScholarGate. (2026, June 3). Semi-supervised Reinforcement Learning (SSRL). ScholarGate. https://scholargate.app/zh/deep-learning/semi-supervised-reinforcement-learning
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- 域自适应强化学习深度学习↔ compare
- 强化学习深度学习↔ compare
- 自监督强化学习深度学习↔ compare
- 半监督式 Transformer深度学习↔ compare
- 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深度学习↔ compare
- 弱监督强化学习深度学习↔ compare