学術論文 |
- "拡大Tchebyshev関数を用いた多目的最適化としての潜在ダイナミクスモデルの学習," 日本ロボット学会誌（レター）, vol.39, no.9, 2021.11.15
- 武田 敏季, 小林 泰介, 杉本 謙二
- "カルバック・ライブラ情報量の非対称性に着目したサンプリングベースモデル予測制御," 日本ロボット学会誌（レター）, 2021.10
- 福本 晃汰, 小林 泰介, 杉本 謙二
- "ツァリス統計に基づく変分オートエンコーダによるスパースな潜在空間の獲得," 日本ロボット学会誌（レター）, 2021.10
- 綿貫 零真, 小林 泰介, 杉本 謙二
- "Bottom-up Multi-agent Reinforcement Learning by Reward Shaping for Cooperative-Competitive Tasks," Applied Intelligence, vol.51, no.7, pp4434-4452, Jul. 2021
- Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto
 [ doi:10.1007/s10489-020-02034-2 ]
- "Safe and Efficient Imitation Learning by Clarification of Experienced Latent Space," Advanced Robotics, vol.35, no.16, pp1012-1027, Jul. 2021
- Hidehito Fujiishi, Taisuke Kobayashi, Kenji Sugimoto
[ doi:10.1080/01691864.2021.1959397 ]
- "Sample-efficient Gear-ratio Optimization for Biomechanical Energy Harvester," International Journal of Intelligent Robotics and Applications, May. 2021
- Taisuke Kobayashi, Yutaro Ikawa, Takamitsu Matsubara
[ doi:10.1007/s41315-021-00170-7 ]
- "Whole-Body Multicontact Haptic Human–Humanoid Interaction Based on Leader–Follower Switching: A Robot Dance of the “Box Step”," Advanced Intelligent Systems, pp2100038, May. 2021
- Taisuke Kobayashi, Emmanuel Dean-Leon, Julio Rogelio Guadarrama-Olvera, Florian Bergner, Gordon Cheng
[ doi:10.1002/aisy.202100038 ]
- "t-Soft Update of Target Network for Deep Reinforcement Learning," Neural Networks, vol.136, pp63-71, Apr. 2021
- Taisuke Kobayashi, Wendyam Eric Lionel Ilboudo
[ doi:10.1016/j.neunet.2020.12.023 ]
- "5分で分かる！？有名論文ナナメ読み「Sergey Levine: Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review」," 情報処理, vol.62, no.1, pp34-35, 2021.1
- 小林 泰介
- "Robust Stochastic Gradient Descent with Student-t Distribution based First-order Momentum," IEEE Transactions on Neural Networks and Learning Systems, Dec. 2020
- Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
[ doi:10.1109/TNNLS.2020.3041755 ]
- "q-VAE for Disentangled Representation Learning and Latent Dynamical Systems," IEEE Robotics and Automation Letters, vol.5, no.4, pp5669-5676, Oct. 2020
- Taisuke Kobayashi
 [ NAISTレポジトリ ] [ doi:10.1109/LRA.2020.3010206 ]
- "Reinforcement Learning for Quadrupedal Locomotion with Design of Continual-Hierarchical Curriculum," Engineering Applications of Artificial Intelligence, vol.95, pp103869, Oct. 2020
- Taisuke Kobayashi, Toshiki Sugino
[ doi:10.1016/j.engappai.2020.103869 ]
- "Towards Physical Interaction-based Sequential Mobility Assistance using Latent Generative Model of Movement State," Advanced Robotics, Oct. 2020
- Shunki Itadera, Taisuke Kobayashi, Jun Nakanishi, Tadayoshi Aoyama, Yasuhisa Hasegawa
[ doi:10.1080/01691864.2020.1844797 ]
- "リレー解説 機械学習の可能性《第7回》機械学習と制御：連続行動空間における強化学習," 計測と制御, vol.58, no.10, pp806-810, 2019.10
- 小林 泰介
- "Delays in perception and action for improving walk–run transition stability in bipedal gait," Nonlinear Dynamics, vol.97, no.2, pp1685-1698, Jul. 2019
- Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Yasuhisa Hasegawa, Toshio Fukuda
[ doi:10.1007/s11071-019-05097-0 ]
- "Student-t policy in reinforcement learning to acquire global optimum of robot control," Applied Intelligence, vol.49, no.12, pp4335-4347, Jun. 2019
- Taisuke Kobayashi
[ doi:10.1007/s10489-019-01510-8 ]
- "Virtual-Dynamics-based Reference Gait Speed Generator for Limit-Cycle-based Bipedal Gait," ROBOMECH Journal, vol.5, pp1-17, Aug. 2018
- Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda
- "Unified bipedal gait for autonomous transition between walking and running in pursuit of energy minimization," Robotics and Autonomous Systems, vol.103, pp27-41, Mar. 2018
- Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda
|
