Reinforcement Learning based on State Space Model using Growing Neural Gas for a Mobile Robot

被引：2

作者：

Arai, Tomoyuki ^{[1
]}

Toda, Yuichiro ^{[2
]}

Iwasa, Mutsumi ^{[1
]}

Shao, Shuai ^{[1
]}

Tonomura, Ryuta ^{[1
]}

Kubota, Naoyuki ^{[1
]}

机构：

[1] Tokyo Metropolitan Univ, Grad Sch Syst Design, Tokyo, Japan

[2] Okayama Univ, Grad Sch Nat Sci Technol, Okayama, Japan

来源：

2018 JOINT 10TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS (SCIS) AND 19TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS (ISIS) | 2018年

关键词：

Reinforcement Learning; Self-organization; Machine Learning; Mobile Robot; State Space;

D O I：

10.1109/SCIS-ISIS.2018.00220

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the application of Reinforcement Learning to real tasks, a state space construction is an important problem. In order to use in real world environment, we need to deal with the problem of continuous information. Therefore, we proposed a Growing Neural Gas method based on state space construction model. In our system, the agent constructs State Space Model from its own experience autonomously. Furthermore, it can reconstruct a suitable state space to adapt complication of the environment. Through the experiments, we showed that our method using state space performs as well as the conventional method by using a smaller number of states.

引用

页码：1410 / 1413

页数：4

共 50 条

[31] Tracking control for mobile robot based on deep reinforcement learning
Zhang Shansi
Wang Weiming
2019 2ND INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS 2019), 2019, : 155 - 160
[32] Mobile robot navigation control based on hierarchical reinforcement learning
Department of Automation, University of Science and Technology of China, Hefei 230027, China
Nanjing Hangkong Hangtian Daxue Xuebao, 2006, 1 (70-75):
[33] Deep Reinforcement Learning Based Mobile Robot Navigation:A Review
Kai Zhu
Tao Zhang
Tsinghua Science and Technology, 2021, 26 (05) : 674 - 691
[34] Enhancement of Mobile Robot Stability and Hardware Based on Reinforcement Learning
Kim, Ki-Seo
Moon, Jeong-Hwan
Lee, Jang-Myung
ICAROB 2018: PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON ARTIFICIAL LIFE AND ROBOTICS, 2018, : 302 - 305
[35] State estimation for mobile robot using neural networks
Chouraqui, S.
Benyettou, M.
Journal of Applied Sciences, 2009, 9 (22) : 3957 - 3965
[36] Mobile Robot Heading Adjustment Using Radial Basis Function Neural Networks Controller and Reinforcement Learning
Bayar, Goekhan
Konukseven, E. Ilhan
Koku, A. Bugra
PROCEEDINGS OF THE 4TH WSEAS/IASME INTERNATIONAL CONFERENCE ON DYNAMICAL SYSTEMS AND CONTROLS, 2008, : 169 - 174
[37] Growing Neural Gas based Traversability Clustering for an Autonomous Robot
Ozasa, Koki
Toda, Yuichiro
Matsuno, Takayuki
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
[38] Reinforcement learning neural network to the problem of autonomous mobile robot obstacle avoidance
Huang, BQ
Cao, GY
Guo, M
PROCEEDINGS OF 2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-9, 2005, : 85 - 89
[39] Multi-Robot Cooperation Based on Continuous Reinforcement Learning with Two State Space Representations
Yasuda, Toshiyuki
Ohkura, Kazuhiro
Yamada, Kazuaki
2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013), 2013, : 4470 - 4475
[40] Reinforcement learning and ART2 neural network based collision avoidance system of mobile robot
Fan, J
Wu, GF
Ma, F
Liu, J
ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 2, 2004, 3174 : 35 - 41

← 1 2 3 4 5 →