3rd-year Ph.D. students

Yu Suetomi Development of high-temperature superconducting magnet winding method with thermal and mechanical resistance to quenching in high magnetic fields
Yusuke Nakata
(Frontier Science)
A study on inverse reinforcement learning in multiple markov decision processes
Keiichi Namikoshi Estimation of agent-specific action rules and incentives based on trajectories

1st-year Ph.D. students

Daiko Kishikawa
(Frontier Science)
Estimation of intension via deep inverse reinforcement learning

2nd-year Master's students

Toya Kamatani Proposal of dynamic pricing scheme for one-way car sharing service that considers convenience for both businesses and users
Kousuke Nishi Behavioral incentive correction method considering bounded rationality

1st-year Master's students

Takumi Saiki Adaptive traffic light control via multi-objective reinforcement learning
Tomohiro Hayashi Method of reinforcement learning for leading people flow in urban space
Ayumu Mimata Detection of suspicious behaviors based on intention inferred from human trajectories using inverse reinforcement learning

4th-year Bachelor's students

Rintaro Imamura Maneuvering an automatic underwater vehicle in an uncertain environment via reinforcement learning
Seiya Takano Extraction of "design know-how" by introducing graph representation of training data
Naoya Takayama Estimating weight of each objective for multi-objective sequential decision-making in continuous state space
Ryuuichi Tsutani Acquiring policy to avoid multiple objects moving around via reinforcement learning
Naoto Horie Verification of an autonomous drone control system for gathering information in disaster areas
Ichiru Matsuda Analysis for the design of urban spaces considering human stream