Research of security system for amusement facilities based on improved multi-agent cooperative reinforcement learning method

Based on the depth analysis of fault and accident causation of amusement facilities, integrating artificial intelligence, intelligent control and measurement techniques, the paper brings forward amusement facilities security system on multi-agent, which is composed by series of subagents. An improved cooperative reinforcement learning approach is proposed in this paper to solve the problem of slow learning speed and poor convergence of the traditional agent learning method. The algorithm is based on Friend-or-Foe Q-Learning. It doesn't do reinforcement learning until the clustering analysis is used to pre-treat both state space and action space, to reduce the space dimension. This advanced approach not only avoids the duplication of work and blind search of the action set but also enhances the learning speed of the agents and the convergence of the algorithm greatly. Thereby achieve more efficient security monitoring and warning-forecasting of amusement facilities. Simulation experiment shows that the system can effectively predict equipment faults, reduce accident incidence rate and increase security operation levels.