Taisuke Kobayashi
Cited by
Cited by
Robust stochastic gradient descent with student-t distribution based first-order momentum
WEL Ilboudo, T Kobayashi, K Sugimoto
IEEE Transactions on Neural Networks and Learning Systems 33 (3), 1324-1337, 2020
T-soft update of target network for deep reinforcement learning
T Kobayashi, WEL Ilboudo
Neural Networks 136, 63-71, 2021
Student-t policy in reinforcement learning to acquire global optimum of robot control
T Kobayashi
Applied Intelligence 49 (12), 4335-4347, 2019
Unified bipedal gait for autonomous transition between walking and running in pursuit of energy minimization
T Kobayashi, K Sekiyama, Y Hasegawa, T Aoyama, T Fukuda
Robotics and Autonomous Systems 103, 27-41, 2018
Locomotion selection strategy for multi-locomotion robot based on stability and efficiency
T Kobayashi, T Aoyama, M Sobajima, K Sekiyama, T Fukuda
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems c, 2013
Whole]Body Multicontact Haptic Human–Humanoid Interaction Based on Leader–Follower Switching: A Robot Dance of the gBox Steph
T Kobayashi, E Dean-Leon, JR Guadarrama-Olvera, F Bergner, G Cheng
Advanced Intelligent Systems 4 (2), 2100038, 2022
Selection algorithm for locomotion based on the evaluation of falling risk
T Kobayashi, T Aoyama, K Sekiyama, T Fukuda
IEEE Transactions on Robotics 31 (3), 750-765, 2015
Adaptive speed controller using swing leg motion for 3-D limit-cycle-based bipedal gait
T Kobayashi, T Aoyama, Y Hasegawa, K Sekiyama, T Fukuda
Nonlinear Dynamics 84, 2285-2304, 2016
Bottom-up multi-agent reinforcement learning by reward shaping for cooperative-competitive tasks
T Aotani, T Kobayashi, K Sugimoto
Applied Intelligence 51 (7), 4434-4452, 2021
Proximal policy optimization with relative pearson divergence
T Kobayashi
2021 IEEE International Conference on Robotics and Automation (ICRA), 8416-8421, 2021
Continual learning exploiting structure of fractal reservoir computing
T Kobayashi, T Sugino
Artificial Neural Networks and Machine Learning–ICANN 2019: Workshop and c, 2019
Adaterm: Adaptive t-distribution estimated robust moments towards noise-robust stochastic gradient optimizer
WEL Ilboudo, T Kobayashi, T Matsubara
Available at SSRN 4349092, 2022
Meta-optimization of bias-variance trade-off in stochastic model learning
T Aotani, T Kobayashi, K Sugimoto
IEEE Access 9, 148783-148799, 2021
Optimistic reinforcement learning by forward Kullback–Leibler divergence optimization
T Kobayashi
Neural Networks 152, 169-180, 2022
Towards deep robot learning with optimizer applicable to non-stationary problems
T Kobayashi
2021 IEEE/SICE International Symposium on System Integration (SII), 190-194, 2021
q-VAE for disentangled representation learning and latent dynamical systems
T Kobayashis
IEEE Robotics and Automation Letters 5 (4), 5669-5676, 2020
Reduction of noise and vibration in drum type washing machine using Q-learning
T Shimizu, H Funakoshi, T Kobayashi, K Sugimoto
Control Engineering Practice 122, 105095, 2022
Adaptive and multiple time-scale eligibility traces for online deep reinforcement learning
T Kobayashi
Robotics and Autonomous Systems 151, 104019, 2022
Reinforcement learning for quadrupedal locomotion with design of continual–hierarchical curriculum
T Kobayashi, T Sugino
Engineering Applications of Artificial Intelligence 95, 103869, 2020
Tadam: A robust stochastic gradient optimizer
WEL Ilboudo, T Kobayashi, K Sugimoto
arXiv preprint arXiv:2003.00179, 2020
The system can't perform the operation now. Try again later.
Articles 1–20