| 基于变学习率的多agent学习算法的研究 |
| |
| 引用本文： | 李琳娜.基于变学习率的多agent学习算法的研究[J].长春工程学院学报(自然科学版),2009,10(4):81-83. |
| |
| 作者姓名： | 李琳娜 |
| |
| 作者单位： | 长春工程学院电气与信息工程学院,长春,130012 |
| |
| 摘 要： | 对在动态学习的环境中的IGA算法做了研究,改进了梯度方向上的步长恒定不变的不足,引入了变学习率,并介绍了调节学习率的方法——WoLF原则,加速其收敛。最后根据该方法,对Q学习算法做了改进,并通过仿真试验证明了算法的有效性。
|
| 关 键 词： | 多agent学习 变学习率 Q学习 |
The study of multi - agent learning algorithm based on variable learning rate |
| |
| LI Lin-na.The study of multi - agent learning algorithm based on variable learning rate[J].Journal of Changchun Institute of Technology(Natural Science Edition),2009,10(4):81-83. |
| |
| Authors: | LI Lin-na |
| |
| Institution: | LI Lin - na ( Faculty of Electrical ＆ Information Engineering, Changchun Institute of Technology, Changchun 130012, China) |
| |
| Abstract: | This paper studied the IGA algorithm in a dynamic learning environment,and improved the insufficiency of step constantly invariable in the gradient direction.The variable learning rate and the WoLF principle to adjust learning rate were introduced in order to accelerate its convergence.Finally the Q learning algorithm was improved based on this method and the validity of the algorithm was proved through the simulation testing. |
| |
| Keywords: | multi-agent study variable learning rate Q-learning |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
