T. Shibuya

Reinforcement learning in the environment where optimal action value function is partly discontinuous

Shingo Shibusawa, T. Shibuya, 2016, 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

A Case Study of Assessing Button Bits Failure through Wavelet TransformUsing Rock Drilling Induced Noise Signals

H. Jang, Y. Kawamura, T. Shibuya, 2017 .

A method deciding topological relationship for self-organizing maps by persistent homology analysis

Takeshi Shibuya, Rentaro Futagami, T. Shibuya, 2016, 2016 55th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

Inferring Underlying Manifold of Low Density Data using Adaptive Interpolation

Noritaka Yamada, Takeshi Shibuya, T. Shibuya, 2020, ICAART.

Complex-valued Profit Sharing with Multiple Phase Changes

Takeshi Shibuya, Tomoki Hamagami, Shingo Shimada, 2009 .

Reinforcement Learning to Efficiently Recover Control Performance of Robots Using Imitation Learning After Failure

S. Kobayashi, T. Shibuya, 2022, 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

Complex-Valued Reinforcement Learning: a Context-Based Approach for POMDPs

Takeshi Shibuya, Tomoki Hamagami, T. Shibuya, 2011 .

An intelligent guide vehicle by fuzzy guide target considering tiredness

Seiji Yasunobu, Takeshi Shibuya, Takayuki Ogawa, 2013, The SICE Annual Conference 2013.

Partially Observable Markov Decision Process and Reinforcement Learning

Takeshi Shibuya, T. Shibuya, 2013 .

Disturbance Observable Reinforcement Learning that Compensates for Changes in Environment

T. Shibuya, Seong-Bae Kim, 2022, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE).

Classification for sequential data involving human trial and error

Hiroaki Yano, Takeshi Shibuya, Shintaro Enoki, 2017, 2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

Q-learning in continuous state-action space with redundant dimensions by using a selective desensitization neural network

Takeshi Shibuya, Masahiko Morita, Takaaki Kobayashi, 2014, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS).

Topological Visualization Method for Understanding the Landscape of Value Functions and Structure of the State Space in Reinforcement Learning

Takeshi Shibuya, Yuki Nakamura, T. Shibuya, 2020, ICAART.

Profit sharing reducing the occurrences of accidents by predicted action-safety degree

Takeshi Shibuya, Junki Tamaru, T. Shibuya, 2015, 2015 10th Asian Control Conference (ASCC).

A Method of Generalization of State Space Construction for Multirobots with Different Sensor Configurations

Takeshi Shibuya, Tomoki Hamagami, T. Shibuya, 2008 .

Efficiency of Reinforcement Learning using Polarized Regime by Variational Autoencoder

T. Shibuya, Masato Nakai, 2022, 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE).