Multi-agent cooperation framework based on deep reinforcement learning

Abstract

The invention discloses a multi-agent collaboration framework based on deep reinforcement learning, which comprises an agent, a billboard, and a an actor-critic-based deep reinforcement learning module, a next moment state calculation module. The agent is defined by a current state, a speed and an expected target; the billboard is responsible for storing, updating and transmitting information; anactor in the Actor-Critic-based deep reinforcement learning module selects a proper action according to the current environment state and the state of an agent, and training learning is continuously carried out through Critic in combination with evaluation given by the state sequence of each agent, so that an optimal control strategy is obtained; and the next moment state calculation module respectively calculates the state of each agent at the next moment according to the current state of each agent and the taken action, and interacts with the billboard. The multi-agent cooperation frameworkbased on deep reinforcement learning provided by the invention has relatively good expandability and relatively high universality, and can provide a technical scheme for realizing diverse multi-agentcooperation.

Description

[0001] Technical field: [0002] 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. [0003] Background technique: [0004] 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 broa...

AI Technical Summary

Problems solved by technology

[0004] 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