3rd-year Ph.D. students

Daiko Kishikawa Estimation of intension via deep inverse reinforcement learning
Dan Zhou Evolutionary Computation for Multi-objective Reinforcement Learning
Du Jiqing Adaptive Control System via Deep Reinforcement Learning

2nd-year Ph.D. students

Takumi Saiki Traffic signal control via multi-objective reinforcement learning

1st-year Ph.D. students

Wataru Mogi Mechanism Design: Realization of Traffic Equilibrium Allocation via Inverse Reinforcement Learning

2nd-year Master's students

Akinori Tamura Multi-objective reinforcement learning for nonconvex Pareto front estimation
Ryota Toriumi Integrated Reinforcement Learning and Control Theory for Automatic Railway Operation
Yuki Mori Improving scalability of multi-agent deep reinforcement learning
Yuta Mori Cooperative Measurements in Multi-Agent Deep Reinforcement Learning

1st-year Master's students

Takeshi Kunieda Identification of good structure/bad structure situations for optimal hazard avoidance control
Masaharu Saito Identification of multiple intentions latent in heterogeneous multi-agent trajectories
Kentaro Sakai Off-line Reinforcement Learning for Acquiring Robust Control Strategies
Keiju Tazawa Estimation of preference order for behavior change

4th-year Undergrad's students

Yuta Ono Utility Estimation Based on Action History Using Decision Transformer
Yuta Tokuhiro Consideration of ChatGPT and human tagging characteristics of FAQs for realization of automatic response system
Hayato Chujo Realization of environmental protection and comfort by introducing event-driven control
Takuya Maniwa Generation of optimal measures based on multiple suboptimal measures
Shota Shinohara Robustness Verification of Automatic Railway Control by Reinforcement Learning
Kouta Minoshima Imitation Learning from Small Data
Misato Kobayashi Automated Vehicle Formation Driving: Using Attention to Maintain Formation
Kento Nagata System Identification and Design Methods by Introducing Model-Free Reinforcement Learning: ~Complementary Use of Control Theory~
Seitetsu Kumataki DRRL (PID control + deep reinforcement learning) stability improvement by Human Feedback
Yusuke Yasui Introduction of Reinforcement Learning in Horizon Decision Making for Model Predictive Control: ~Complementary Use of Control Theory~