https://www.selleckchem.com/products/ff-10101.html The research of financial systemic risk is an important issue, however the research on the financial systemic risk in ASEAN region lacks. This paper uses the minimum density method to calculate the interbank network of ASEAN countries and uses the node centrality to judge the systemically important banks of various countries. Then the DebtRank algorithm is constructed to calculate the systemic risk value based on the interbank network. By comparing the systemic risk values obtained through the initial impact on the system important banks and non-important banks, we find that the systemic risk tends to reach the peak in the case of the initial impact on the system important banks. Furthermore, it is found that countries with high intermediary centrality and closeness centrality have higher systemic risk. It suggests that the regulatory authorities should implement legal supervision, strict supervision, and comprehensive supervision for key risk areas and weak links.The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. Typically, an agent receives its private observations providing a partial view of the true state of the environment. However, in realistic settings, the harsh environment might cause one or more agents to show arbitrarily faulty or malicious behavior, which may suffice to allow the current coordination mechanisms fail. In this paper, we study a practical scenario of multi-agent reinforcement learning systems considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. The previous state-of-the-art work that coped with extremely noisy environments was designed on the basis that the noise intensity in the environment was known in advance. However, when the noise intensity changes, the existing method has to adjust the configuration of the model t