Fields of Interests
- Robot dynamics and control
- Model-based reinforcement learning
- Numerical optimal control
- Variational inference
Journal Papers
-
T. Hishinuma, K. Senda,
"Importance-weighted variational inference model estimation for offline Bayesian model-based reinforcement learning",
IEEE Access,
vol. 11, pp. 145579-145590, 2023.
-
K. Senda, T. Hishinuma, Y. Tani,
"Approximate Bayesian Reinforcement Learning based on Estimation of Plant",
Autonomous Robots,
vol. 44, no. 5, pp. 845-857, 2020.
-
K. Senda, S. Hattori, T. Hishinuma, T. Kohda,
"Acceleration of Reinforcement Learning by Policy Evaluation Using Nonstationary Iterative Method",
IEEE Transactions on Cybernetics,
vol. 44, no. 12, pp. 2696-2705, 2014.
Peer-reviewed Conference Papers
-
T. Hishinuma, K. Senda,
"Weighted model estimation for offline model-based reinforcement learning",
Neural Information Processing Systems (NeurIPS),
pp. 17789-17800, 2021.
-
T. Hishinuma, K. Senda,
"An Approximate Bayesian Reinforcement Learning Approach Using Robust Control Policy and Tree Search",
International Conference on Automated Planning and Scheduling (ICAPS),
pp. 417-421, 2018.
-
T. Hishinuma, K. Senda,
"Robust and explorative behavior in model-based Bayesian reinforcement learning",
IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL),
2016.
Education
- MEng, Kyoto University, Graduate School of Engineering, Department of Aeronautics and Astronautics, 2015.
- BEng, Kyoto University, Department of Engineering Science, Aeronautics and Astronautics Course, 2013.