arrow
返回

Discrete space reinforcement learning algorithm based on support vector machine classification

delete2018-08-01
delete36
PRE
AI
Y
Yuexuan An
S
Shifei Ding *
S
Songhui Shi
J
Jingcan Li
DOI:10.1016/j.patrec.2018.04.012delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
When facing discrete space learning problems, the traditional reinforcement learning algorithms often have the problems of slow convergence and poor convergence accuracy. Deep reinforcement learning needs a large number of learning samples in its learning process, so it often faces with the problems that the algorithm is difficult to converge and easy to fall into local minimums. In view of the above problems, we apply support vector machines classification to reinforcement learning, and propose an algorithm named Advantage Actor-Critic with Support Vector Machine Classification (SVM-A2C). Our algorithm adopts the actor-critic framework and uses the support vector machine classification as a result of the actor's action output, while Critic uses the advantage function to improve and optimize the parameters of support vector machine. In addition, since the environment is changing all the time in reinforcement learning, it is difficult to find a global optimal solution for the support vector machines, the gradient descent method is applied to optimize the parameters of support vector machine. So that the agent can quickly learn a more precise action selection policy. Finally, the effectiveness of the proposed method is proved by the classical experimental environment of reinforcement learning. It is proved that the algorithm proposed in this paper has shorter episodes to convergence and more accurate results than other algorithms. (C) 2018 Elsevier B.V. All rights reserved.
Keyword:
Support vector machines
Reinforcement learning
Actor-critic
Machine learning
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition Letters 封面图
Pattern Recognition Letters
IF:
3.3
论文数:
8.0K
被引数:
2.0W

机构

暂无机构信息
引用论文

引用论文

err分享
err收藏
Document-level sentiment classification: An empirical comparison between SVM and ANN
err2013-02-01
err456
PREAI
errMoraes, Rodrigo; Valiati, Joao Francisco; Gaviao Neto, Wilson P.
err分享
err收藏
Incremental Support Vector Learning for Ordinal Regression
err2015-07-01
err667
errOAAI
errGu, Bin; Sheng, Victor S.; Tay, Keng Yeow; Romano, Walter; Li, Shuo
err分享
err收藏
学者 查看更多内容