Skip to content

A platform for multi-agent reinforcement learning algorithm training and testing for target tracking problem

Notifications You must be signed in to change notification settings

MartinYuanNJU/MARL_Train-Test_Platform

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

MARL_Train-Test_Platform

A platform for multi-agent reinforcement learning algorithm training and testing for target tracking problem

国家级大学生创新项目算法训练测试仿真平台

在框架之中将现有的主流强化学习算法(DQN,Double DQN,Dueling DQN,Actor-Critic,DDPG,MADDPG)应用到了追踪问题中,并且针对DQN,Double DQN,Dueling DQN,Actor-Critic,DDPG这些传统单智能体强化学习方法,我们分别利用了三种途径:centralized,distributed,parameter-share将它们扩展成为多智能体强化学习算法

设计并实现了高效的实验仿真平台以及一组评判指标,系统性地评价了上述主流强化学习算法以及将传统单智能体强化学习方法扩展为多智能体强化学习算法的三种途径在目标追踪问题上的表现优劣

源代码在master branch下面

About

A platform for multi-agent reinforcement learning algorithm training and testing for target tracking problem

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published