Segmented Actor-Critic-Advantage Architecture for Reinforcement Learning Tasks

被引：0

作者：

Kaloev, Martin ^{[1
]}

Krastev, Georgi ^{[1
]}

机构：

[1] Univ Ruse, Dept Comp Syst & Technol, Ruse, Bulgaria

来源：

TEM JOURNAL-TECHNOLOGY EDUCATION MANAGEMENT INFORMATICS | 2022年 / 11卷 / 01期

关键词：

Reinforcement learning; Q-learning; Actor-critic algorithm; Neuron-like machine architecture;

D O I：

10.18421/TEM111-27

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The article focuses on experiments with a multi module neural networks type of architecture for neuron-like machine used in reinforcing learning. This type of architecture can be used to solve complex robotic or policy optimization tasks and allows segmented storage of trained memory. Such technique speeds up the training process compared to existing actor-critical algorithms.

引用

页码：219 / 224

页数：6

共 50 条

[1] Variational value learning in advantage actor-critic reinforcement learning
Zhang, Yaozhong
Han, Jiaqi
Hu, Xiaofang
Dan, Shihao
[J]. 2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 1955 - 1960
[2] A Parallel Approach to Advantage Actor Critic in Deep Reinforcement Learning
Zhu, Xing
Du, Yunfei
[J]. ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2019, PT II, 2020, 11945 : 320 - 327
[3] Application of Improved Asynchronous Advantage Actor Critic Reinforcement Learning Model on Anomaly Detection
Zhou, Kun
Wang, Wenyong
Hu, Teng
Deng, Kai
[J]. ENTROPY, 2021, 23 (03) : 1 - 22
[4] Fully distributed actor-critic architecture for multitask deep reinforcement learning
Valcarcel Macua, Sergio
Davies, Ian
Tukiainen, Aleksi
De Cote, Enrique Munoz
[J]. KNOWLEDGE ENGINEERING REVIEW, 2021, 36
[5] A World Model for Actor–Critic in Reinforcement Learning
A. I. Panov
L. A. Ugadiarov
[J]. Pattern Recognition and Image Analysis, 2023, 33 : 467 - 477
[6] Locating algorithm of steel stock area with asynchronous advantage actor-critic reinforcement learning
Cho, Young-in
Kim, Byeongseop
Yoon, Hee-Chang
Woo, Jong Hun
[J]. JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING, 2024, 11 (01) : 230 - 246
[7] Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning
Xiao, Yuchen
Lyu, Xueguang
Amato, Christopher
[J]. 2021 INTERNATIONAL SYMPOSIUM ON MULTI-ROBOT AND MULTI-AGENT SYSTEMS (MRS), 2021, : 155 - 163
[8] Selector-Actor-Critic and Tuner-Actor-Critic Algorithms for Reinforcement Learning
Masadeh, Ala'eddin
Wang, Zhengdao
Kamal, Ahmed E.
[J]. 2019 11TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP), 2019,
[9] An Asynchronous Advantage Actor-Critic Reinforcement Learning Method for Stock Selection and Portfolio Management
Kang, Qinma
Zhou, Huizhuo
Kang, Yunfan
[J]. PROCEEDINGS OF THE 2018 2ND INTERNATIONAL CONFERENCE ON BIG DATA RESEARCH (ICBDR 2018), 2018, : 141 - 145
[10] Multi-actor mechanism for actor-critic reinforcement learning
Li, Lin
Li, Yuze
Wei, Wei
Zhang, Yujia
Liang, Jiye
[J]. INFORMATION SCIENCES, 2023, 647

← 1 2 3 4 5 →