Cooperative agent learning method based on multi-agent reinforcement learning

Abstract

The invention relates to a cooperative agent learning method based on multi-agent reinforcement learning. The cooperative agent learning method comprises the steps of 1, resetting a plurality of target environments; 2, initializing a model parameter theta pi of the strategy network pi theta and a model parameter theta f of the global information prediction network f theta; 3, sampling the multipleagents in the multiple environments according to the current strategy pi in the environment, wherein in each step, a plurality of agents in the environment share the same state, and characteristics are extracted from the state by aiming at each agent and then are used as data input by the model; 4, updating the model parameters theta pi and theta f; and step 5, updating until the model convergesor reaches the maximum step number. According to the method, the global feature information is better utilized in the environment that the agents are in the cooperative relationship, and each agent learns to perceive the relationship between the local information and the global information through the model for predicting the global information through the local information, so that the agents canbetter cooperate; therefore, different agents can directly share the model parameters, the model complexity is simplified, and the efficiency is improved.

Description

technical field [0001] The invention relates to the field of machine learning, and more specifically, to a learning method for cooperative agents based on multi-agent reinforcement learning. Background technique [0002] Reinforcement learning is a subfield of machine learning whose goal is to take decision-making actions based on the environment so as to obtain the maximum benefit. Among them, reinforcement learning introduces deep learning technology as a function approximation method for learning value functions and strategies in reinforcement learning, which greatly improves end-to-end performance compared with manual feature extraction, thus solving a series of problems that traditional reinforcement learning cannot solve. , such as on video games, deep reinforcement learning has even achieved performance that exceeds the average human level. [0003] The existing reinforcement learning methods have a relatively mature system, including model-based and model-free metho...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the problems of poor collaboration and low efficiency of multi-agents in a cooperative environment in the above-mentioned prior art, the present invention provides a learning method for cooperative agents based on multi-agent reinforcement learning, which improves the performance of multi-agents in a cooperative environment. Collaboration and efficiency, enhancing the performance of agents

Images