Reinforcement learning based on state space model using growing neural gas for a mobile robot

Tomoyuki Arai, Yuichiro Toda, Iwasa Mutsumi, Shuai Shao, Ryuta Tonomura, Naoyuki Kubota

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems and 19th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1410-1413
Number of pages4
ISBN (Electronic)9781538626337
DOIs
Publication statusPublished - Jul 2 2018
EventJoint 10th International Conference on Soft Computing and Intelligent Systems and 19th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2018 - Toyama, Japan
Duration: Dec 5 2018Dec 8 2018

Publication series

NameProceedings - 2018 Joint 10th International Conference on Soft Computing and Intelligent Systems and 19th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2018

Conference

ConferenceJoint 10th International Conference on Soft Computing and Intelligent Systems and 19th International Symposium on Advanced Intelligent Systems, SCIS-ISIS 2018
Country/TerritoryJapan
CityToyama
Period12/5/1812/8/18

Keywords

  • Mobile Robot
  • Reinforcement Learning
  • Self-organization
  • State Space

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Logic
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Theoretical Computer Science

Fingerprint

Dive into the research topics of 'Reinforcement learning based on state space model using growing neural gas for a mobile robot'. Together they form a unique fingerprint.

Cite this