|
|||||
|
|
| RLAR:基于增强学习的自适应路由算法 | |
| 引用本文： | 郑力明,李晓冬,李小勇. RLAR:基于增强学习的自适应路由算法[J]. 计算机工程与设计, 2011, 32(4): 1190-1194 |
| 作者姓名： | 郑力明 李晓冬 李小勇 |
| 作者单位： | 1. 武警成都指挥学院,信息技术教研室,四川,成都,610213;国防科技大学,计算机学院并行与分布处理,国家重点实验室,湖南,长沙,410073 2. 武警成都指挥学院,科研科,四川,成都,610213 3. 国防科技大学,计算机学院并行与分布处理,国家重点实验室,湖南,长沙,410073 |
| 基金项目： | 国家973重点基础研究发展计划基金，国家自然科学基金，高等学校博士学科点专项科研基金 |
| 摘 要： | 针对当前各种路由算法在广域网环境下由于不能适应各种拓扑环境和负载不均衡时所引起的路由性能不高等问题,提出了一种基于梯度上升算法实现的增强学习的自适应路由算法RLAR。增强学习意味着学习一种策略,即基于环境的反馈信息构造从状态到行为的映射,其本质为通过与环境的交互试验对策略集合进行评估。将增强学习策略运用于网络路由优化中,为路由研究提供了一种全新的思路。对比了多种现有的路由算法,实验结果表明,RLAR能有效提高网络路由性能。 |
| 关 键 词： | 增强学习 路由 梯度上升 马尔可夫决策过程 自适应 |
RLAR:Adaptive routing algorithm based on reinforcement learning |
|
| ZHENG Li-ming,LI Xiao-dong,LI Xiao-yong. RLAR:Adaptive routing algorithm based on reinforcement learning[J]. Computer Engineering and Design, 2011, 32(4): 1190-1194 | |
| Authors: | ZHENG Li-ming LI Xiao-dong LI Xiao-yong |
| Affiliation: | ZHENG Li-ming1,2,LI Xiao-dong3,LI Xiao-yong2(1.Information and Technology Teaching and Researching Section,Chengdu Commanding College of Chinese Armed Police Force,Chengdu 610213,China,2.National Key Laboratory for Parallel and Distributed Processing,School of Computer,National University of Defense Technology,Changsha 410073,3.Research Section,China) |
| Abstract: | Aimed at the poor performance of the current various routing algorithms,due to the poor adaptability to various changing net-work topologies and loads,an adaptive routing algorithm called RLAR is proposed,and the algorithm is based on reinforcement learning which implemented by gradient ascent algorithm.Reinforcement learning means learning a policy that a mapping of states into actions which based on feedback from the environment.The learning can be viewed as browsing a set of policies while evaluating the... |
| Keywords: | reinforcement learning routing gradient ascent MDP adaptive |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |