A multi-agent collaboration framework based on deep reinforcement learning

Abstract

The invention discloses a multi-agent cooperation framework based on deep reinforcement learning, which includes an agent, a billboard, an actor-critic-based deep reinforcement learning module, and a next-moment state calculation module. The agent is defined by the current state, speed and desired goal; the billboard is responsible for the storage, update and transmission of information; in the deep reinforcement learning module based on Actor‑Critic, the actor selects the appropriate action according to the current environment state and the state of the agent itself, and combines each agent through Critic The evaluation given by the state sequence of the state is continuously trained and learned to obtain the optimal control strategy; the next moment state calculation module calculates the state of each agent at the next moment according to the current state of each agent and the action taken, and interacts with the billboard . The multi-agent cooperation framework based on deep reinforcement learning proposed by the present invention has good scalability and strong versatility, and can provide technical solutions for realizing various multi-agent cooperation.

Description

Technical field: [0001] The invention relates to the fields of virtual reality and artificial intelligence, in particular to a multi-agent collaboration framework based on deep reinforcement learning. Background technique: [0002] Multi-agent (that is, intelligent body) system can solve complex and distributed problems, and has advantages in speed, reliability, flexibility and maintainability. It has always been the focus of research in the field of artificial intelligence. Since reinforcement learning does not require environmental modeling , has become the main research method of multi-agent cooperation, but it still faces many challenges when solving multi-agent cooperation with continuous state and action space, such as the problem of "curse of dimensionality" and low learning efficiency. In recent years, with the rapid development of artificial intelligence technology, deep reinforcement learning has attracted more and more attention, because it has broad application p...

AI Technical Summary

Problems solved by technology

[0002] Multi-agent (that is, intelligent body) system can solve complex and distributed problems, and has advantages in speed, reliability, flexibility and maintainability. It has always been the focus of research in the field of artificial intelligence. Since reinforcement learning does not require environmental modeling , has become the main research method of multi-agent collaboration, but it still faces many challenges when solving multi-agent collaboration with continuous state and action space, such as the problem of "curse of dimensionality" and low learning efficiency

Images