Shin Ishii

Nara Institute of Science and Technology, Centre for Research in Engineering Surface Technology, Advanced Telecommunications Research Institute International, Research Organization of Information and Systems, RIKEN Center for Brain Science, Kyoto University, Japan Science and Technology Agency

Papers

17

Total Citations

656

H-Index

9

About

No biography available yet.

Research Focus

Artificial intelligence17 · 656 citations
Computer science17 · 656 citations
Robot14 · 348 citations
Artificial neural network2 · 346 citations
Reinforcement learning13 · 325 citations
Mathematics3 · 289 citations
Mathematical optimization2 · 283 citations
Algorithm2 · 283 citations
Gaussian2 · 283 citations
Regularization (linguistics)1 · 280 citations
Estimator1 · 280 citations
Statistics1 · 280 citations

Key Achievements

9
H-Index
17
Papers
656
Total Citations
39
Avg Citations/Paper
🏆 Most Cited Paper
On-line EM Algorithm for the Normalized Gaussian Network
280 citations · 2000
📈 Most Prolific Year: 2005 (3 Papers)
🤝 Key Collaborators: 39
🏛 Institutions: Nara Institute of Science and Technology, Centre for Research in Engineering Surface Technology, Advanced Telecommunications Research Institute International, Research Organization of Information and Systems, RIKEN Center for Brain Science, Kyoto University

Top Papers

  1. 1
    On-line EM Algorithm for the Normalized Gaussian Network
    280 citations · 2000
  2. 2
    Reinforcement learning for a biped robot based on a CPG-actor-critic method
    118 citations · 2007
  3. 3
    Reinforcement learning for a CPG-driven biped robot
    66 citations · 2004
  4. 4
    Reinforcement Learning for Biped Locomotion
    35 citations · 2002
  5. 5
    A waypoint-based framework in brain-controlled smart home environments: Brain interfaces, domotics, and robotics integration
    34 citations · 2013
  6. 6
    Reinforcement learning for quasi-passive dynamic walking of an unstable biped robot
    30 citations · 2006
  7. 7
    Application of reinforcement learning to balancing of Acrobot
    19 citations · 2003
  8. 8
    Fast and Stable Learning of Quasi-Passive Dynamic Walking by an Unstable Biped Robot based on Off-Policy Natural Actor-Critic
    15 citations · 2006
  9. 9
    Natural Policy Gradient Reinforcement Learning for a CPG Control of a Biped Robot
    15 citations · 2004
  10. 10
    Modeling of human velocity habituation for a robotic wheelchair
    9 citations · 2014

Key Collaborators

YNYutaka Nakamura8 shared papersMSMasa-aki Sato5 shared papersTSTomohiro Shibata5 shared papersTMTakeshi Mori3 shared papersJYJunichiro Yoshimoto2 shared papersYMYoichi Morales2 shared papersNHNorihiro Hagita2 shared papersYNYoshitaka Nakamura2 shared papersJAJamilah Abdur-Rahim1 shared papersYNYukihiro Noda1 shared papersTTTomoya Tamei1 shared papersKHKentarou Hitomi1 shared papersAKAkihiro Kubo1 shared papersMKMotoaki Kawanabe1 shared papersNKNagasrikanth Kallakuri1 shared papersTITetsushi Ikeda1 shared papersMSMasaaki Sato1 shared papersKHKentaro Hitomi1 shared papersSFShuichi FUKUNAGA1 shared papersTMTakeshi Mori1 shared papers
Not generated yet