An acquisition of the relation between vision and action using self-organizing map and reinforcement learning

被引：0

作者：

Terada, K ^{[1
]}

Takeda, H ^{[1
]}

Nishida, T ^{[1
]}

机构：

[1] Nara Inst Sci & Technol, Grad Sch Informat Sci, Nara 63001, Japan

来源：

1998 SECOND INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ELECTRONIC SYSTEMS, KES'98 PROCEEDINGS, VOL 1 | 1998年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An agent must acquire internal representation appropriate for its task, environment, sensors. As a learning algorithm, reinforcement learning is often utilized to acquire the relation between sensory input and action. Learning agents in the real world using visual sensors is often confronted with critical problem how to build necessary and sufficient state space for the agent to execute the task. fn this paper, we propose acquisition of relation between vision and action using Visual State-Action Map (VSAM). VSAM is the application of Self-Organizing Map (SOM). Input image data is mapped on the node of learned VSAM. Then VSAM outputs the appropriate action for the state, We applied VSAM to real robot. The experimental result shows that a real robot avoids the wall while moving around the environment.

引用

页码：429 / 434

页数：6

共 50 条

[31] Clustering method using self-organizing map
Endo, Masahiro
Ueno, Masahiro
Tanabe, Takaya
Yamamoto, Manabu
Neural Networks for Signal Processing - Proceedings of the IEEE Workshop, 2000, 1 : 261 - 270
[32] Self-Organizing Agents for Reinforcement Learning in Virtual Worlds
Kang, Yilin
Tan, Ah-Hwee
2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[33] A New Self-Organizing Map with Continuous Learning Capability
Hikawa, Hiroomi
Ito, Hidetaka
Maeda, Yutaka
2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 2163 - 2168
[34] Multistrategy Self-Organizing Map Learning for Classification Problems
Hasan, S.
Shamsuddin, S. M.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2011, 2011
[35] A Self-Organizing Map-Based Adaptive Traffic Light Control System with Reinforcement Learning
Kao, Ying-Cih
Wu, Cheng-Wen
2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 2060 - 2064
[36] Learning a Self-organizing Map Model on a Riemannian Manifold
Yu, D. J.
Hancock, E. R.
Smith, W. A. P.
MATHEMATICS OF SURFACES XIII, 2009, 5654 : 375 - +
[37] A growing parallel self-organizing map for unsupervised learning
Valova, I
Szer, D
Georgieva, N
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1924 - 1929
[38] Path Searching of a Robot Manipulator Using Reinforcement Learning and Self-Organizing Maps
Hiraoka, Kenji
Aoyagi, Seiji
SERVICE ROBOTICS AND MECHATRONICS, 2010, : 341 - 346
[39] Syntactical self-organizing map
Grigore, O
COMPUTATIONAL INTELLIGENCE: THEORY AND APPLICATIONS, 1997, 1226 : 101 - 109
[40] Randomized Self-Organizing Map
Rougier, Nicolas P.
Detorakis, Georgios Is.
NEURAL COMPUTATION, 2021, 33 (08) : 2241 - 2273

← 1 2 3 4 5 →