A self-organized fuzzy-neuro reinforcement learning system for continuous state space for autonomous robots

• 大林, 正直

• 呉本, 尭

• 小林, 邦和

Abstract

International Conference on Computational Intelligence for Modelling, Control and Automation : CIMCA 2008, Vienna, Austria, December 10-12, 2008.

This paper proposes the system that combines self-organized fuzzy-neural networks with reinforcement learning system (Q-learning, stochastic gradient ascent : SGA) to realize the autonomous robot behavior learning for continuous state space. The self-organized fuzzy neural network works as adaptive input state space classifier to adapt the change of environment, the part of reinforcement learning has the learning ability corresponding to rule for the input state space . Simultaneously, to simulate the real environment the robot has ability to estimate own-position. Finally, it is clarified that our proposed system is effective through the autonomous robot behavior learning simulation by using the khepera robot simulator.

Journal

• Proceedings of International Conference on Computational Intelligence for Modelling, Control and Automation

  Proceedings of International Conference on Computational Intelligence for Modelling, Control and Automation 2008 551-556, 2008-12

  Institute of Electrical and Electronics Engineers

Details

• CRID: 1050574047121063168
• NII Article ID: 120006665594
• Web Site: https://petit.lib.yamaguchi-u.ac.jp/17554
• Text Lang: en
• Article Type: conference paper
• Data Source:
  • IRDB
  • CiNii Articles
  • KAKEN