no code implementations • 4 Mar 2024 • Yota Hashizume, Koshi Oishi, Kenji Kashima
Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e. g., maximum entropy reinforcement learning known as Soft Actor-Critic.
no code implementations • 28 Feb 2024 • Koshi Oishi, Yota Hashizume, Tomohiko Jimbo, Hirotaka Kaji, Kenji Kashima
Considering this, there is a pressing need for research to enhance the robustness of network systems.
no code implementations • 10 Jan 2024 • Ryuta Moriyasu, Sho Kawaguchi, Kenji Kashima
In this paper, we propose a discrete-time dynamical controller, incorporating specific modifications to the PDG approach, and present stability conditions relevant to the resulting sampled-data system.
no code implementations • 30 Nov 2023 • Ryuta Moriyasu, Masayuki Kusunoki, Kenji Kashima
Research on control using models based on machine-learning methods has now shifted to the practical engineering stage.
no code implementations • 20 Jan 2023 • Yu Kawano, Kenji Kashima
Contraction theory formulates the analysis of nonlinear systems in terms of Jacobian matrices.
no code implementations • 5 Dec 2022 • Koshi Oishi, Yota Hashizume, Tomohiko Jimbo, Hirotaka Kaji, Kenji Kashima
In this study, we proposed a method for designing a resilient logistics network based on entropy regularization.
no code implementations • 11 Apr 2022 • Kaito Ito, Kenji Kashima
We consider an entropy-regularized version of optimal density control of deterministic discrete-time linear systems.
no code implementations • 24 Mar 2022 • Kaito Ito, Kenji Kashima
To avoid such approximation, in this paper, we reformulate the KL control problem for continuous spaces so that it does not require unrealistic assumptions.
no code implementations • 18 Mar 2022 • Kenji Kashima, Ryota Yoshiuchi, Yu Kawano
When neural networks are used to model dynamics, properties such as stability of the dynamics are generally not guaranteed.
no code implementations • 9 Jul 2021 • Ryuta Moriyasu, Taro Ikeda, Sho Kawaguchi, Kenji Kashima
This paper aims to improve the reliability of optimal control using models constructed by machine learning methods.