通信受限下的协作式多智能体强化学习方法OA

To address the problem that most existing collaborative multi-agent reinforcement learning meth-ods adopt overly idealized communication assumptions,a cooperative multi-agent reinforcement learning meth-ods under communication constraints is proposed.First,a more realistic communication constrained environ-ment is constructed by introducing random information loss and additive Gaussian white noise disturbance.Then,a residual connection-based value decomposition method is proposed,leveraging residual structures to enhance the robustness of system against communication quality fluctuations and observational noise.Finally,the proposed method is validated in a communication constrained test environment built on the StarCraft multi-agent challenge benchmark.Experimental results show that the proposed method performs excellently under various communication-constrained scenarios,significantly outperforming current mainstream multi-agent rein-forcement learning methods.