Multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning

Abstract

The invention provides a multi-agent adversarial decision-making method based on cooperative reinforcement learning and transfer learning, and the method is characterized in that the method comprisesthe following steps: defining the state space S = {s1, s2,..., sn} of an agent; setting an action space A to be equal to {a1, a2,..., an}; setting a value function matrix of the agent reinforcement learning model; calculating a value function sequence corresponding to the current state st by using an action evaluator, and selecting a corresponding action at through an action selector based on simulated annealing and softmax strategy; meanwhile, the state of the intelligent agent is changed, and the intelligent agent is transferred to the next state st + 1. After the action at is executed, theintelligent agent obtains a reward signal rt from the environment; the loss of experience storage can be reduced through a weight sharing mode, and the adversarial decision-making efficiency is improved. Through the migration learning method based on the attenuation function, the agent can reuse previous experience with a gradually decreasing probability, and the migration learning migrates the previously trained action evaluator weight to more adversarial decision scenes, thereby improving the generalization of the learning model.

Description

technical field [0001] The invention belongs to the field of machine learning and intelligent computing, and in particular relates to a multi-agent confrontation decision-making method based on cooperative reinforcement learning and transfer learning. Background technique [0002] With the continuous development of artificial intelligence and intelligent control technology, machine learning has been widely used in many research fields such as intelligent robots, unmanned driving, industrial Internet of Things, and edge computing, and plays an important role. Multi-agent confrontation decision-making is a current research hotspot in the field of intelligent computing. Common multi-agent confrontation decision-making includes robot soccer and underwater robot games. However, as the multi-agent confrontation decision-making environment tends to become more complex and fuzzy, and the task environment has more uncertainties, the classic multi-agent confrontation decision-making m...

AI Technical Summary

Problems solved by technology

[0005] Based on the problems mentioned in the background technology, the present invention proposes a multi-agent confrontation decision-making method based on cooperative reinforcement learning and transfer learning, which overcomes the slow convergence speed and poor scene adaptability in the traditional method, and it is difficult to complete the scheduled decision efficiently. The deficiencies of the task; its specific technical content is as follows:

Images