Consideration on robotic giant-swing motion generated by reinforcement learning

  title={Consideration on robotic giant-swing motion generated by reinforcement learning},
  author={Masayuki Hara and Naoto Kawabe and Naoki Sakai and Jian Huang and Hannes Bleuler and Tetsuro Yabuta},
  journal={2009 IEEE/RSJ International Conference on Intelligent Robots and Systems},
This study attempts to make a compact humanoid robot acquire a giant-swing motion without any robotic models by using reinforcement learning; only the interaction with environment is available. Generally, it is widely said that this type of learning method is not appropriated to obtain dynamic motions because Markov property is not necessarily guaranteed during the dynamic task. However, in this study, we try to avoid this problem by embedding the dynamic information in the robotic state space… CONTINUE READING


Publications referenced by this paper.
Showing 1-7 of 7 references

Control of Real Acrobot by Learning the Switching Rule of Multiple Controllers

  • J. Yoshimoto M. Nishimura, Y. Tokita, Nakamura Y, S. Ishii
  • Trans . of the IEICE . A
  • 1997

Giant swing via forward upward circling of the Acrobat - robot Efficient reinforcement learning : Model - based Acrobot control

  • H. Sato Michitsuji, M. Yamakita
  • 1995

Reinforcement learning using stochastic gradient algorithm and its application to robots

  • S. Kobayashi
  • IEE Japan Trans . on Electronics , Information…
  • 1995

A Study of the Brachiation Type of Mobile Robot ( 7 th Report , Behavior Learning for Hierarchical Behavior - based Controller )

  • Y. Ito Hasegawa, T. Fukuda

Learning Method for Multiple - Control for Robot Behavior

  • Y. Hasegawa

Similar Papers

Loading similar papers…