Research On Multi-agent Cooperative Control Based On MADDPG Algorithm

Traditional industrial robots are based on precise mathematical models,and their control methods usually set specific tasks in a fixed environment.However,such a traditional control system does not have adaptability and generalization.When the environment in which the robot is located changes slightly,the robot cannot complete the task accurately.Therefore,intelligent control algorithms have gradually become a research focus of machine control.With the continuous development of reinforcement learning and deep learning,the application of deep reinforcement learning algorithms to robot control has attracted the attention of researchers.This paper first introduces the control principle of traditional mechanical control and the development of deep reinforcement learning,and elaborates the research background and research purpose of this topic.Secondly,in the Mu Jo Co environment based on the physics engine,a Deterministic Policy Gradient(DDPG)algorithm is used to focus on the robustness and versatility of the DDPG algorithm in a single agent environment.However,with the instability of the environment caused by the increase in the number of agents,general deep reinforcement learning has certain difficulties in the joint action space.Finally,in order to solve this problem,a task of four robotic arms to reach the target position through cooperative control was designed,and Multi-Agent Deep Deterministic Policy Gradient(MADDPG)was used to train in Mu Jo Co.The experimental results show that each robotic arm can complete the task through autonomous learning to obtain information and accumulate experience.At the same time,the model has a good convergence effect,indicating that the MADDPG algorithm has good performance in complex environments and successfully learned multiagent collaboration strategy.