Mehdi Dastani，荷兰乌特勒支大学人工智能教授，智能系统负责人，AI大师系统首席程序设计师。他致力于智能系统的编程，决策理论，认知与互动系统以及监控系统的计算模型与应用创新研究。
Prof. Mehdi Dastani
The main referenced paper is Safe Reinforcement Learning via Shielding. Download here.
Participants: Beishui Liao, Zelai Yao, Jieting Luo (Luora), Dongheng Chen, Yiqi Shen, Chonghui Li, Landuo Dou, Jiayi Li.
First, Dongheng Chen presented the homework of last seminar.
Then, Zelai Yao reviewed Alternative Time Temporal Logic (ATL) and gave a presentation on Norm Specification.
