Current Issue : October-December Volume : 2021 Issue Number : 4 Articles : 5 Articles
In the adaptive traffic signal control (ATSC), reinforcement learning (RL) is a frontier research hotspot, combined with deep neural networks to further enhance its learning ability. The distributed multiagent RL (MARL) can avoid this kind of problem by observing some areas of each local RL in the complex plane traffic area. However, due to the limited communication capabilities between each agent, the environment becomes partially visible. This paper proposes multiagent reinforcement learning based on cooperative game (CG-MARL) to design the intersection as an agent structure. The method considers not only the communication and coordination between agents but also the game between agents. Each agent observes its own area to learn the RL strategy and value function, then concentrates the Q function from different agents through a hybrid network, and finally forms its own final Q function in the entire large-scale transportation network. The results show that the proposed method is superior to the traditional control method....
Low-carbon technological innovation is the main means to develop a low-carbon economy, and network knowledge sharing and collaborative innovation is an effective model for the development of low-carbon technologies. First of all, this article adopts a decision-making experiment and evaluation laboratory method and interpretation structure model, combines the two methods, extracts the advantages of the two, and discards the shortcomings of the two, thus constructing a new optimized and upgraded interpretation structure model. We give methods to explore the main influencing factors of collaborative innovation of lowcarbon technologies for online knowledge sharing. Based on the industrial network knowledge sharing and cooperation network environment, the network evolution game model of network knowledge sharing knowledge collaboration is constructed to study the rewards and punishments, the profit distribution rate, the knowledge potential difference, and the parameter pairing of the network knowledge sharing cooperation network structure in the process of network knowledge sharing and collaborative knowledge innovation. (e influence of the network knowledge sharing cooperation strategy is obtained through simulation to change the size of the relevant parameters so that the network knowledge sharing cooperation agent chooses the network evolution game of the sharing strategy to realize the optimal evolutionary stable strategy. According to the simulation results, this article proposes suggestions from the following aspects, aiming to improve the overall knowledge synergy effect of the network knowledge sharing and cooperation network....
In the process of cultural dissemination, the dissemination of false information will have a negative impact on the entire environment. In this case, it is an effective method to regulate the behavior of cultural dissemination participants. Based on the community network structure and the improved classic network communication model, this paper constructs the susceptibleinfected- recovered (SIR) model for the grassroots communication of engineering safety culture and discusses the law of grassroots transmission of engineering safety culture. )e communication process is simulated, and it is concluded that a good engineering safety culture will be the first to be covered by low-level engineering safety culture in the process of dissemination. With a modularity coefficient of 0.5 as the boundary, it will affect the scale of good safety culture in different directions; the dissemination infection rate of low-level engineering safety culture changes in the same direction with the speed and scale of transmission; the maximum transmission scale of low-level engineering safety culture does not decrease with the increase of the initial value of the susceptible state. When the initial value of the immune state is 15%, the low-level safety culture scale is the lowest value of 0.135, which is the low initial value of employees with low-level engineering safety culture and is more conducive to control its maximum spread. It also puts forward management recommendations for the subjects and objects of the grassroots dissemination of engineering safety culture. )is paper transforms cultural communication into an evolutionary game model, uses a game tree to describe it, and analyzes that the model has a Nash equilibrium point by adding a penalty function to the income matrix. )is model can encourage cultural communication participants to take honest behaviors, effectively restrain the transmission of false information, and promote a virtuous circle of cultural communication....
Sport games are among the oldest and best established genres of computer games. Sport-inspired environments, such as RoboCup, have been used for AI benchmarking for years. We argue that, in spite of the rise of increasingly more sophisticated game genres, team sport games will remain an important testbed for AI benchmarking due to two primary factors. First, there are several genrespecific challenges for AI systems that are neither present nor emphasized in other types of games, such as team AI and frequent replanning. Second, there are unmistakable nonskill-related goals of AI systems, contributing to player enjoyment, that are most easily observed and addressed within a context of a team sport, such as showing creative and emotional traits. We analyze these factors in detail and outline promising directions for future research for game AI benchmarking, within a team sport context...
Public health emergencies are more related to the safety and health of the public. For the management of the public health emergencies, all parties’ cooperation is the key to preventing and controlling the emergencies. Based on the assumption of bounded rationality, we formulate a tripartite evolutionary game model, involving the local government, the enterprises, and the public, for the public health emergency, e.g., COVID-19. +e evolutionary stable strategies under different conditions of the tripartite evolutionary game are explored, and the effect from different factors on the decision-makings of participants for public health emergencies is also analyzed. Numerical analysis results show that formulating reasonable subsidy measures, encouraging the participation of the public, and enforcing the punishment to enterprises for their negative behaviors can prompt three parties to cooperate in fighting against the epidemic. Our work enriches an understanding of the governance for the public health emergency and provides theoretical support for the local government and related participants to make proper decisions in public health emergencies....
Loading....