Taisuke Kobayashi

Nara Institute of Science and Technology, Nagoya University, National Institute of Informatics, Fraunhofer Institute for Cognitive Systems, Meijo University, The Graduate University for Advanced Studies, SOKENDAI, Kobe University

Papers

46

Total Citations

464

H-Index

10

About

No biography available yet.

Research Focus

Artificial intelligence46 · 464 citations
Computer science46 · 464 citations
Reinforcement learning14 · 246 citations
Machine learning14 · 239 citations
Mathematics22 · 233 citations
Robot28 · 201 citations
Artificial neural network7 · 175 citations
Algorithm10 · 153 citations
Robustness (evolution)9 · 148 citations
Control theory (sociology)18 · 135 citations
Outlier6 · 124 citations
Simulation14 · 118 citations

Key Achievements

10
H-Index
46
Papers
464
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
t-soft update of target network for deep reinforcement learning
68 citations · 2021
📈 Most Prolific Year: 2019 (6 Papers)
🤝 Key Collaborators: 38
🏛 Institutions: Nara Institute of Science and Technology, Nagoya University, National Institute of Informatics, Fraunhofer Institute for Cognitive Systems, Meijo University, The Graduate University for Advanced Studies, SOKENDAI

Top Papers

  1. 1
    t-soft update of target network for deep reinforcement learning
    68 citations · 2021
  2. 2
    Robust Stochastic Gradient Descent With Student-t Distribution Based First-Order Momentum
    67 citations · 2020
  3. 3
    Student-t policy in reinforcement learning to acquire global optimum of robot control
    34 citations · 2019
  4. 4
    Whole‐Body Multicontact Haptic Human–Humanoid Interaction Based on Leader–Follower Switching: A Robot Dance of the “Box Step”
    23 citations · 2021
  5. 5
    Selection Algorithm for Locomotion Based on the Evaluation of Falling Risk
    20 citations · 2015
  6. 6
    Optimistic reinforcement learning by forward Kullback–Leibler divergence optimization
    20 citations · 2022
  7. 7
    Locomotion selection strategy for multi-locomotion robot based on stability and efficiency
    19 citations · 2013
  8. 8
    Adaptive speed controller using swing leg motion for 3-D limit-cycle-based bipedal gait
    17 citations · 2016
  9. 9
    Reinforcement learning for quadrupedal locomotion with design of continual–hierarchical curriculum
    12 citations · 2020
  10. 10
    Latent Representation in Human–Robot Interaction With Explicit Consideration of Periodic Dynamics
    11 citations · 2022

Key Collaborators

TATadayoshi Aoyama15 shared papersYHYasuhisa Hasegawa14 shared papersTFToshio Fukuda13 shared papersKSKosuke Sekiyama13 shared papersKSKenji Sugimoto5 shared papersZLZhiguo Lü5 shared papersWEWendyam Eric Lionel Ilboudo4 shared papersTATakumi Aotani3 shared papersJRJ. Rogelio Guadarrama-Olvera3 shared papersGCGordon Cheng3 shared papersEDEmmanuel Dean‐Leon3 shared papersJNJun Nakanishi2 shared papersHFHidehito Fujiishi2 shared papersSIShunki Itadera2 shared papersFBFlorian Bergner2 shared papersTITetsunari Inamura2 shared papersTSToshiki Sugino2 shared papersTFTakanori Fukao1 shared papersOTOta Tomoro1 shared papersKFKota Fukumoto1 shared papers
Not generated yet