Learning a dynamic policy by using policy gradient: Application to biped walking

被引：0
|
作者：
Matsubara, Takamitsu [1 ,2 ]
Morimoto, Jun [2 ,3 ]
Nakanishi, Jun [2 ,3 ]
Sato, Masa-Aki [2 ,4 ]
Doya, Kenji [2 ,4 ,5 ]
机构：
[1] Nara Institute of Science and Technology, Ikoma, 630-0101, Japan
[2] ATR Computational Neuroscience Laboratories, Kyoto, 619-0288, Japan
[3] ICORP, JST, Kyoto, 619-0288, Japan
[4] CREST, JST, Kyoto, 619-0288, Japan
[5] Initial Research Project, Okinawa Institute of Science and Technology, Gushikawa, 904-2234, Japan
来源：
Systems and Computers in Japan | 2007年 / 38卷 / 04期
关键词：
24;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Journal article (JA)
引用
收藏
页码：25 / 38
相关论文
共 50 条
  • [1] Off-Policy Natural Policy Gradient Method for a Biped Walking Using a CPG Controller
    Nakamura, Yutaka
    Mori, Takeshi
    Tokita, Yoichi
    Shibata, Tomohiro
    Ishii, Shin
    [J]. JOURNAL OF ROBOTICS AND MECHATRONICS, 2005, 17 (06) : 636 - 644
  • [2] A Stochastic Policy Gradient Based Adaptive Control for Biped Walking
    Song, Sumian
    Yan, Gangfeng
    Tang, Chong
    Wang, Zidong
    Lin, Zhiyun
    [J]. 2015 34TH CHINESE CONTROL CONFERENCE (CCC), 2015, : 3224 - 3229
  • [3] Biped dynamic walking using reinforcement learning
    Benbrahim, H
    Franklin, JA
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 1997, 22 (3-4) : 283 - 302
  • [4] Learning sensory feedback to CPG with policy gradient for biped locomotion
    Matsubara, T
    Morimoto, J
    Nakanishi, J
    Sato, MA
    Doya, K
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-4, 2005, : 4164 - 4169
  • [5] Learning CPG-based biped locomotion with a policy gradient method: Application to a humanoid robot
    Endo, Gen
    Morimoto, Jun
    Matsubara, Takamitsu
    Nakanishi, Jun
    Cheng, Gordon
    [J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2008, 27 (02): : 213 - 228
  • [6] Learning CPG-based biped locomotion with a policy gradient method
    [J]. Matsubara, T. (takam-m@atr.jp), (Inst. of Elec. and Elec. Eng. Computer Society, 445 Hoes Lane - P.O.Box 1331, Piscataway, NJ 08855-1331, United States):
  • [7] Learning CPG-based biped locomotion with a policy gradient method
    Matsubara, Takamitsu
    Morimoto, Jun
    Nakanishi, Jun
    Sato, Masa-aki
    Doya, Kenji
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2006, 54 (11) : 911 - 920
  • [8] Natural policy gradient reinforcement learning for a CPG control of a biped robot
    Nakamura, Y
    Mori, T
    Ishii, S
    [J]. PARALLEL PROBLEM SOLVING FROM NATURE - PPSN VIII, 2004, 3242 : 972 - 981
  • [9] Learning CPG-based biped locomotion with a policy gradient method
    Matsubara, T
    Morimoto, J
    Nakanishi, J
    Sato, M
    Doya, K
    [J]. 2005 5TH IEEE-RAS INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS, 2005, : 208 - 213
  • [10] Biped Walking Learning from Imitation Using Dynamic Movement Primitives
    Rosado, Jose
    Silva, Filipe
    Santos, Vitor
    [J]. ROBOT 2015: SECOND IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2, 2016, 418 : 185 - 196
12345