Intelligent agent control method and device based on reinforcement learning

Abstract

The invention relates to an intelligent agent control method and device based on reinforcement learning. The method comprises the steps of obtaining current local observation of an intelligent agent;taking the current local observation of the intelligent agent as the input of a reinforcement learning model, and obtaining the current execution action of the intelligent agent output by the reinforcement learning model; controlling an intelligent agent to execute the current execution action of the intelligent agent; according to the technical scheme provided by the invention, the strategy learning process in a large-scale multi-intelligent system can be effectively simplified, the number and types of intelligent agents are easy to expand, and the method has potential value in large-scale real world application.

Description

technical field [0001] The invention relates to the field of multi-agent cooperative control, in particular to an agent control method and device based on reinforcement learning. Background technique [0002] In recent years, the rapid development of deep reinforcement learning has made researchers interested in multi-agent reinforcement learning, hoping that it can solve complex and large-scale problems, such as vehicle autonomous driving, resource allocation, swarm robots, human machine interaction, etc. At present, certain research results have been achieved in multi-agent reinforcement learning, such as communication and natural language processing, multi-agent games, traffic control, social dilemmas, etc. At the same time, more and more researchers began to pay attention to the research of large-scale multi-agent reinforcement learning. In large-scale multi-agent systems, a large number of agents with different goals and complex interactions between agents pose great ...

AI Technical Summary

Problems solved by technology

However, in a large-scale multi-agent environment, especially in an environment with many types of agents, the effect of the algorithm is still limited.

Images