Preservation and Application of Acquired Knowledge Using Instance-based Reinforcement Learning

• Sakanoue Junki

  Hiroshima University

• Yasuda Toshiyuki

  Hiroshima University

• Ohkura Kazuhiro

  Hiroshima University

Abstract

We have been developing a reinforcement learning technique called BRL as an approach to autonomous specialization, which is a new concept in cooperative multi-robot systems. BRL has a mechanism for autonomously segmenting the continuous state and action space. However, as in other machine learning approaches, overfitting is occasionally observed after successful learning. This paper proposes a technique to sophisticatedly utilize messy knowledge acquired using BRL. The proposed technique is expected to show better robustness against environmental changes. We investigate the proposed technique by conducting computer simulations of a cooperative carrying task.

Journal

• SCIS & ISIS

  SCIS & ISIS 2010 (0), 576-581, 2010

  Japan Society for Fuzzy Theory and Intelligent Informatics

Keywords

• Multi-robot Systems
• Reinforcement Learning
• Support Vector Machine

Details

• CRID: 1390001205589898368
• NII Article ID: 130005019631
• DOI: 10.14864/softscis.2010.0.576.0
• Text Lang: en
• Data Source:
  • JaLC
  • CiNii Articles
• Abstract License Flag: Disallowed