Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space

Tomoyuki Arai, Yuichiro Toda, Naoyuki Kubota

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

Abstract

In the application of Reinforcement Learning to real tasks, the construction of state space is a significant problem. In order to use in the real-world environment, we need to deal with the problem of continuous information. Therefore, we proposed a method of the construction of state space using Growing Neural Gas. In our method, the agent constructs a state space model from its own experience autonomously. Furthermore, it can reconstruct the suitable state space model to adapt the complication of the environment. Through the experiments, we showed that Reinforcement Learning could be performed efficiently by successively updating the state space model according to the environment.

Original languageEnglish
Title of host publicationProceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019
PublisherIEEE Computer Society
ISBN (Electronic)9781728128160
DOIs
Publication statusPublished - Jul 2019
Event18th International Conference on Machine Learning and Cybernetics, ICMLC 2019 - Kobe, Japan
Duration: Jul 7 2019Jul 10 2019

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume2019-July
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference18th International Conference on Machine Learning and Cybernetics, ICMLC 2019
CountryJapan
CityKobe
Period7/7/197/10/19

Keywords

  • Machine learning
  • Mobile robot
  • Reinforcement learning
  • Self-Organization
  • State space

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space'. Together they form a unique fingerprint.

Cite this