Voot Tangkaratt
Voot Tangkaratt
Postdoc researcher @ RIKEN AIP, Japan.
ms.k.u-tokyo.ac.jp üzerinde doğrulanmış e-posta adresine sahip
Başlık
Alıntı yapanlar
Alıntı yapanlar
Yıl
Fast and scalable bayesian deep learning by weight-perturbation in adam
ME Khan, D Nielsen, V Tangkaratt, W Lin, Y Gal, A Srivastava
arXiv preprint arXiv:1806.04854, 2018
902018
Efficient sample reuse in policy gradients with parameter-based exploration
T Zhao, H Hachiya, V Tangkaratt, J Morimoto, M Sugiyama
Neural computation 25 (6), 1512-1547, 2013
372013
Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
V Tangkaratt, S Mori, T Zhao, J Morimoto, M Sugiyama
Neural networks 57, 128-140, 2014
282014
Model-based reinforcement learning with dimension reduction
V Tangkaratt, J Morimoto, M Sugiyama
Neural Networks 84, 1-16, 2016
172016
Hierarchical reinforcement learning via advantage-weighted information maximization
T Osa, V Tangkaratt, M Sugiyama
arXiv preprint arXiv:1901.01365, 2019
162019
Imitation learning from imperfect demonstration
YH Wu, N Charoenphakdee, H Bao, V Tangkaratt, M Sugiyama
arXiv preprint arXiv:1901.09387, 2019
152019
TD-regularized actor-critic methods
S Parisi, V Tangkaratt, J Peters, ME Khan
Machine Learning 108 (8-9), 1467-1501, 2019
132019
Guide actor-critic for continuous control
V Tangkaratt, A Abdolmaleki, M Sugiyama
arXiv preprint arXiv:1705.07606, 2017
132017
Direct conditional probability density estimation with sparse feature selection
M Shiga, V Tangkaratt, M Sugiyama
Machine Learning 100 (2-3), 161-182, 2015
122015
Conditional density estimation with dimensionality reduction via squared-loss conditional entropy minimization
V Tangkaratt, N Xie, M Sugiyama
Neural computation 27 (1), 228-254, 2015
102015
Vprop: Variational inference using rmsprop
ME Khan, Z Liu, V Tangkaratt, Y Gal
arXiv preprint arXiv:1712.01038, 2017
92017
Trial and error: Using previous experiences as simulation models in humanoid motor learning
N Sugimoto, V Tangkaratt, T Wensveen, T Zhao, M Sugiyama, J Morimoto
IEEE Robotics & Automation Magazine 23 (1), 96-105, 2016
92016
Variational adaptive-Newton method for explorative learning
ME Khan, W Lin, V Tangkaratt, Z Liu, D Nielsen
arXiv preprint arXiv:1711.05560, 2017
82017
Policy search with high-dimensional context variables
V Tangkaratt, H van Hoof, S Parisi, G Neumann, J Peters, M Sugiyama
Thirty-First AAAI Conference on Artificial Intelligence, 2017
72017
Efficient reuse of previous experiences in humanoid motor learning
N Sugimoto, V Tangkaratt, T Wensveen, T Zhao, M Sugiyama, J Morimoto
2014 IEEE-RAS International Conference on Humanoid Robots, 554-559, 2014
72014
Direct estimation of the derivative of quadratic mutual information with application in supervised dimension reduction
V Tangkaratt, H Sasaki, M Sugiyama
Neural Computation 29 (8), 2076-2122, 2017
62017
Sufficient dimension reduction via direct estimation of the gradients of logarithmic conditional densities
H Sasaki, V Tangkaratt, M Sugiyama
Asian Conference on Machine Learning, 33-48, 2016
62016
Sufficient dimension reduction via direct estimation of the gradients of logarithmic conditional densities
H Sasaki, V Tangkaratt, M Sugiyama
Asian Conference on Machine Learning, 33-48, 2016
62016
Active deep Q-learning with demonstration
SA Chen, V Tangkaratt, HT Lin, M Sugiyama
Machine Learning, 1-27, 2019
42019
Variational imitation learning with diverse-quality demonstrations
V Tangkaratt, B Han, ME Khan, M Sugiyama
International Conference on Machine Learning, 9407-9417, 2020
22020
Sistem, işlemi şu anda gerçekleştiremiyor. Daha sonra yeniden deneyin.
Makaleler 1–20