具有指数图信息通信的大规模情境多智能体强化学习OA

Multi-agent reinforcement learning(MARL)demonstrates excellent performance in cooperative tasks.However,in large-scale multi-agent systems(MAS)with complex interaction relationships,traditional MARL al-gorithms perform poorly due to the lack of efficient communication mechanisms.To enhance the performance of MARL in large-scale MAS,this paper proposes an episodic MARL algorithm with exponential graph information communication(EMAGIC).First,this paper designs a one-peer exponential graph-based communication topology,where each agent communicates with only one other agent at each time step and transmits messages to all agents through a cyclic communication link.Second,this paper constructs a graph information communication mechanism that uses a gated recurrent unit to encode messages across multiple time steps and optimizes the encoded features of the messages by maximizing the mutual information between messages of different agents at the same time step.Fi-nally,this paper builds an independent episodic memory(EM)module to establish the correspondence between av-erage returns and global states for constructing a memory bank,and constructs the loss function by using the error between the EM target and the mean of individual values.Experimental results in multiple large-scale multi-agent environments show that EMAGIC consistently outperforms advanced MARL baseline methods.