본문 바로가기
HOME> 논문 > 논문 검색상세

논문 상세정보

Multi-Dimensional Reinforcement Learning Using a Vector Q-Net - Application to Mobile Robots

Kiguchi, Kazuo   (Department of Advanced Systems Control Engineering, Saga UniversityUU0015120  ); Nanayakkara, Thrishantha   (Department Advanced Systems Control Engineering, Saga UniversityUU0015120  ); Watanabe, Keigo   (Department Micro System Engineering, Nagoya UniversityUU0014196  ); Fukuda, Toshio   (Department Micro System Engineering, Nagoya UniversityUU0014196  );
  • 초록

    Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.


  • 주제어

    Reinforcement learning .   Q-learning .   multi-dimensional evaluation .   neural networks .   intelligent robot.  

  • 참고문헌 (13)

    1. A neural substrate of prediction and reward , W. Schultz;P. Dayan;P.R. Montague , Science / v.275,pp.1593-1599,
    2. Estimation of internal parameters of rigid body links of manipulators , C. H. An;C. G. Atkeson;J. M. Hollerbach , Aartificial Intelligence Memo 887 / v.,pp.,
    3. R. S. Sutton;A. G. Barto , Reinforcement Learning / v.,pp.,
    4. Learning from delayed rewards , C. J. C. H Watkins , Ph. D. Dissertation, Cambridge University / v.,pp.,
    5. Purposive behavior acquisition for a real robot by vision-based reinforcement learning , M. Asada;S. Noda;S. Tawaratumida;K. Hosoda , Machine Learning / v.23,pp.279-303,
    6. Learning architecture for real robotic systems Extension of connectionist q-learning for continuous robot control domain , F. Saito;T. Fukuda , Proc. of IEEE International Conference on Robotics and Automation / v.,pp.27-32,
    7. Automatic programming of behavior-based robots using reinforcement learning , S. Mahadevan;J. Connell , Proc. of 9th National Conf. on Artificial Intelligence / v.,pp.768-773,
    8. Reinforcement learning for robots using neural networks , L. J. Lin , Ph. D. Dissertation, Cambridge Mellon University / v.,pp.,
    9. Interaction and intelligeng behavior , M. J. Mataric , Ph. D. Dissertation, MIT / v.,pp.,
    10. Acquiring robot skills via reinforcement learning , V. Gullapalli;J. A. Franklin;H. Benbrahim , IEEE Control Systems Magazine / v.14,pp.13-24,
    11. A sensor-based navigation for a mobile robot using fuzzy logic and reinforcement learning , H. K. Beom;H. S. Cho , IEEE Trans. on Systems, Man, and Cybernetics / v.25,pp.464-477,
    12. Module-based reinforcement learning: experiments with a real robot , Z. Kalmar;C. Szepesvari;A. Lorincz , Machine Learning / v.31,pp.55-85,
    13. Multiple reward criterion for cooperative behavior acquisition in a multiagent environment , E. Uchibe;M. Asada , Proc. of IEEE International Conf. on Systems, Man, and Cybernetics / v.,pp.VI710-VI715,

 활용도 분석

  • 상세보기

    amChart 영역
  • 원문보기

    amChart 영역

원문보기

무료다운로드
  • NDSL :
  • 제어로봇시스템학회 : 저널
유료다운로드

유료 다운로드의 경우 해당 사이트의 정책에 따라 신규 회원가입, 로그인, 유료 구매 등이 필요할 수 있습니다. 해당 사이트에서 발생하는 귀하의 모든 정보활동은 NDSL의 서비스 정책과 무관합니다.

원문복사신청을 하시면, 일부 해외 인쇄학술지의 경우 외국학술지지원센터(FRIC)에서
무료 원문복사 서비스를 제공합니다.

NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.

이 논문과 함께 출판된 논문 + 더보기