作者：Lee, Bruce D.; Zhang, Thomas T. C. K.; Hassani, Hamed; Matni, Nikolai
作者单位：University of Pennsylvania
摘要：Efforts by the reinforcement learning community to close the sim-to-real gap have resulted in policy optimization objectives, which are distinct from, although related to, existing objectives in robust control, such as H-infinity methods. The disparity from the familiar control methods makes it challenging to make rigorous claims about these methods, and to predict the implications on performance of training a policy with a particular level of robustness. This in turn makes selecting the level...
作者：Zhong, Wenjing; Zhao, Jinjing; Hu, Hesuan
作者单位：Xidian University; Nanyang Technological University; Xi'an Jiaotong University
摘要：Security of system behavior is a kind of information flow security, which is achieved by confusing the intruders via the indistinguishability of system behaviors. Noninterference is a typical notion to describe information flow security, for which multilevel intransitive noninterference (MINI) is an advanced variant. Since there is a lack of rigorous approach to assessing MINI, this article achieves so via observability theory. For systems modeled by labeled Petri nets (LPNs), two MINI propert...
