首页 / 深度学习 / 域自适应强化学习 Machine learning Deep learning / NLP / CV
域自适应强化学习 域自适应强化学习（DARL）通过使在一种环境或域中训练的策略能够有效地迁移和泛化到不同但相关的目标域，从而扩展了标准强化学习。它通过对齐、自适应或域随机化技术来解决域偏移问题——即训练和部署之间的动力学、观测或奖励结构存在差异——从而减少了在目标域收集昂贵经验的需要。
速览
Originator Multiple contributors (Taylor & Stone 2009 survey; Kim et al. 2020 among key formalizations)
Year 2009–2020
Type Transfer-based RL paradigm
DataType State-action trajectories from source and target domains
Subfamily Deep learning / NLP / CV 本页目录
Method map The neighbourhood of related methods — select a node to explore.
来源 Kim, K., Kim, H., Lim, H., & Choi, J. (2020). Domain Adaptive Reinforcement Learning with Model-Based Approach. arXiv preprint arXiv:2102.03170. link ↗ Domain adaptation. Wikipedia. link ↗ 如何引用本页 APA BibTeX RIS 复制
ScholarGate. (2026, June 3). Domain-Adaptive Reinforcement Learning. ScholarGate. https://scholargate.app/zh/deep-learning/domain-adaptive-reinforcement-learning
下载 BibTeX 下载 RIS
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.
Compare side by side → 发现本页有问题？报告或提出修改建议 →
ScholarGate — Domain-adaptive reinforcement learning (Domain-Adaptive Reinforcement Learning). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/domain-adaptive-reinforcement-learning · 数据集： https://doi.org/10.5281/zenodo.20539026