Multi-agent federated cooperation method based on deep reinforcement learning

A reinforcement learning, multi-agent technology, applied in machine learning, software deployment, instrumentation, etc., can solve problems such as slow model training process, multi-agent dimensional disaster, and increased time-consuming
CN112465151APending Publication Date: 2021-03-09YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA
0 Cites 19 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA
Publication Date
2021-03-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multi-agent federated cooperation method based on deep reinforcement learning. The method comprises the following steps: S1, establishing a deep reinforcement learning modelfor each agent; S2, establishing a corresponding neural network for the intelligent agent; S3, interacting the intelligent agent with the environment, storing the decision experience in an experiencepool, and updating a local neural network model according to a stochastic gradient descent method; S4, transmitting local neural network model parameters to a cooperation platform; S5, aggregating theparameters uploaded by the intelligent agents, and returning a result to each intelligent agent to update the parameters; S6, performing soft update by the intelligent agent to obtain latest local model parameters; and S7, repeating step S3 to S6 until the target task is completed. According to the intelligent agent, while environment exploration and decision making are carried out through deep reinforcement learning, learning experience of other intelligent agents is obtained through the federated learning technology, so that the learning efficiency of the intelligent agents is effectively improved, and the cooperation overhead between the intelligent agents is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention belongs to the field of artificial intelligence. Specifically aiming at the problems of large collaboration overhead and low collaboration efficiency faced in the process of multi-agent collaboration under complex tasks, a multi-agent federation collaboration method based on deep reinforcement learning is designed. Learning technology, reducing the overhead in the multi-agent collaboration process based on deep reinforcement learning, and improving the efficiency of multi-agent collaboration. Background technique

[0002] In recent years, artificial intelligence technology has developed rapidly and has been widely used. Among them, the agent (Agent) based on deep reinforcement learning is one of the key directions of current research. It perceives the surrounding environmental information and makes intelligent decisions, so as to realize the interaction with the environment and complete the corresponding tasks.

[0003] In practi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More