Cooperative Game-based Intelligent Actions Making for Constrained Multi-agent System

In this paper, an intelligent actions-making model for cooperative games is proposed. This model aims to prevent system breakdowns triggered by many agents, which is a dilemma prevalent in multi-agent systems (MAS) across various practical situations. A widely accepted issue in the domain is that reinforcement learning methods require vast training data Acquiring this data can be costly and time-intensive. Notably, existing game theory methods present challenges, including incomplete information about the agents’ current strategies and reliance on computationally intensive solutions to determine equilibrium points. To address these concerns, this paper offers several novel contributions. First, we introduce a new intelligent actions-making model designed for large-scale MAS, ensuring they remain effective and efficient. Second, to enhance system robustness and adaptability in intricate scenarios, especially under saturation constraints, we incorporate forward prediction for more precise actions-making. Our simulations, conducted with nine agents, attest to the efficiency of the proposed model.