Safe and Efficient Control: A Subgraph-Augmented Hierarchical Reinforcement Learning Framework for Dynamically Reconfigurable Battery Systems
发布时间:2026-09-24
点击次数:
- 发表刊物:
- In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. IJCAI 2026. (CCF-A)
- 关键字:
- AI4Science, Energy Storage
- 摘要:
- 该工作通过将均衡控制任务进行层次化分解,并引入提取自拓扑结构的子图先验作为归纳偏置规避无效探索,实现满足复杂运行约束的拓扑重构动作生成。
- 第一作者:
- 谢锴
- 通讯作者:
- 张志宏(通讯作者)
- 论文类型:
- (CCF-A)
- 是否译文:
- 否



