Discrete space reinforcement learning algorithm based on twin support vector machine classification
Discrete space reinforcement learning algorithm based on twin support vector machine classification
复制标题
DOI：
10.1016/j.patrec.2022.11.017
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Wenguo Wu;Zhengchun Zhou;A. R. Adhikary;Bapi Dutta
中科院分区：
文献类型：
--
作者：
Wenguo Wu;Zhengchun Zhou;A. R. Adhikary;Bapi Dutta
近年来，强化学习（RL）已成为各种机器学习算法的关键组成部分之一。然而，传统RL算法在小规模离散空间环境下收敛速度和精度不足。最近，An et al.提出了一种基于支持向量机（SVM）的强化学习算法（Pattern Recognit. Lett. 111（2018）30-35），其采用了AdvantageActor-Critic（A2 C）框架，并提高了离散空间中收敛的速度和精度。由于双支持向量机（TWSVMs）相对于支持向量机的优势，本文提出了一种基于TWSVM分类的强化学习算法。该算法采用了一种改进的A2 C框架，其中有多个演员和一个单一的批评。最后，我们比较了所提出的算法与现有的一些算法在传统的强化学习环境中的性能。有趣的是，该算法优于现有的算法在收敛速度和精度。
Reinforcement learning (RL) has become one of the key component of various machine learning algorithms in recent years. However, traditional RL algorithms lack convergence speed and accuracy in small-scale discrete space environment. Recently An et al. proposed RL algorithm based on support vector machines (SVMs) (Pattern Recognit. Lett. 111 (2018) 30-35) which adopts the Advantage Actor-Critic (A2C) framework and improves the speed and accuracy of convergence in discrete space. Owing to the advantages of twin support vector machines (TWSVMs) over SVMs, in this paper, we propose a RL algorithm based on TWSVM classification. The proposed algorithm adopts a modified A2C framework, where there are multiple Actors and a single Critic. Finally, we compare the performance of the proposed algorithm with some existing algorithms in traditional RL environment. Interestingly, the proposed algorithm outperforms the existing algorithms in terms of convergence speed and accuracy.