Graph neural network-based reinforcement learning cluster swarming control method

Abstract

The invention discloses a reinforcement learning cluster swarming control method based on a graph neural network. The method comprises the following steps: establishing a cluster swarming control model; determining a topological structure feature representation method of the cluster; determining an observation information feature representation method of the intelligent agent; designing a state space, a behavior space and a return function; designing a strategy network and evaluation network model in a deep reinforcement learning algorithm; designing an algorithm framework and a network parameter updating method; and designing a training process of a cluster swarming control algorithm. The cluster swarming control algorithm is realized by means of the deep reinforcement learning technology, topological structure features and observation information features of the cluster are extracted by using the graph neural network, the convergence speed of the cluster swarming control algorithm and the adaptive capacity to the dynamic environment are effectively improved, and meanwhile, the stability of the algorithm under the interference of control noise and the like can be ensured.

Description

technical field [0001] The patent of the present invention belongs to the field of multi-agent clusters and reinforcement learning, and is a deep reinforcement learning cluster swarming control method based on graph neural network, which involves cluster topology feature extraction, state and action space construction, reward function and training in reinforcement learning Process design and a series of methods. Background technique [0002] Swarm swarming control has very important application and scientific value, such as adaptive control of unmanned aerial vehicles and unmanned vehicle swarms. The current swarming control methods lack the effective use of system topology information, and the equivalence between agents is not considered in the method design. The dynamic changes of the system topology and random noise interference in the control system greatly weaken the control system. Therefore, it is an important research direction for multi-agent swarming control to im...

AI Technical Summary

Problems solved by technology

The current swarming control methods lack the effective use of system topology information, and the equivalence between agents is not considered in the method design, the dynamic changes of system topology and random noise interference in the control system greatly weaken the control Therefore, improving the efficiency of the swarming control algorithm and achieving the convergence of the topology structure and consistent speed in the shortest time is an important research direction for the swarming control of multi-agent clusters.

Images