Knowledge Commons of Institute of Automation,CAS
Explainable Reinforcement Learning via a Causal World Model | |
Yu ZY(余忠蔚)![]() ![]() | |
2023-08 | |
会议名称 | International Joint Conference on Artificial Intelligence |
会议录名称 | Proceedings of the 32nd International Joint Conference on Artificial Intelligence |
页码 | 4540-4548 |
会议日期 | 2023-08-22 |
会议地点 | 中国澳门 |
摘要 | Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior knowledge of the causal structure of the environment. The model captures the influence of actions, allowing us to interpret the long-term effects of actions through causal chains, which present how actions influence environmental variables and finally lead to rewards. Different from most explanatory models which suffer from low accuracy, our model remains accurate while improving explainability, making it applicable in model-based learning. As a result, we demonstrate that our causal model can serve as the bridge between explainability and learning. |
关键词 | 强化学习 可解释人工智能 因果推理 |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 机器学习 |
国重实验室规划方向分类 | 可解释人工智能 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56585 |
专题 | 多模态人工智能系统全国重点实验室 |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yu ZY,Ruan JQ,Xing DP. Explainable Reinforcement Learning via a Causal World Model[C],2023:4540-4548. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
0505.pdf(850KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论