-
Constructing Differentiable Predictive Models for MPC and RL using Functional Modeling and Dynamic Simulators
Shumpei Kubosawa, Junya Ikemoto, Takashi Onishi, Yoshimasa Tsuruoka
Proceedings of International Workshop on Functional Modeling and Safety Related Issues of Socio-Technical Systems p. 17-19 2024年3月 研究論文(研究会,シンポジウム資料等)
-
Deep Reinforcement Learning Based Networked Control with Network Delays for Signal Temporal Logic Specifications.
Junya Ikemoto, Toshimitsu Ushio
IEEE ETFA p. 1-8 2022年 研究論文(国際会議プロシーディングス)
-
Deep Reinforcement Learning Under Signal Temporal Logic Constraints Using Lagrangian Relaxation
Junya Ikemoto, Toshimitsu Ushio
IEEE Access Vol. 10 p. 114814-114828 2022年 研究論文(学術雑誌)
-
Continuous deep Q-learning with a simulator for stabilization of uncertain discrete-time systems
Junya Ikemoto, Toshimitsu Ushio
Nonlinear Theory and Its Applications, IEICE Vol. 12 No. 4 p. 738-757 2021年 研究論文(学術雑誌)
出版者・発行元:Institute of Electronics, Information and Communications Engineers (IEICE)
-
Application of deep reinforcement learning to networked control systems with uncertain network delays
Junya Ikemoto, Toshimitsu Ushio
Nonlinear Theory and Its Applications, IEICE Vol. 11 No. 4 p. 480-500 2020年 研究論文(学術雑誌)
出版者・発行元:Institute of Electronics, Information and Communications Engineers ({IEICE})
-
Control of Discrete-Time Chaotic Systems with Policy-Based Deep Reinforcement Learning.
Junya Ikemoto, Toshimitsu Ushio
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Vol. 103-A No. 7 p. 885-892 2020年 研究論文(学術雑誌)
-
Model-free Control of Chaos with Continuous Deep Q-learning.
Junya Ikemoto, Toshimitsu Ushio
CoRR Vol. abs/1907.07775 2019年 研究論文(学術雑誌)
-
Networked Control of Nonlinear Systems under Partial Observation Using Continuous Deep Q-Learning.
Junya Ikemoto, Toshimitsu Ushio
58th IEEE Conference on Decision and Control(CDC) p. 6793-6798 2019年 研究論文(国際会議プロシーディングス)
出版者・発行元:IEEE