Multi-agent reinforcement learning in decision making
● Our team is using reinforcement learning to support optimal decision-making in personalized and complex medical situations, and our ability to continuously learn is providing significant value in healthcare.
● We have been conducting research on ROI, EEG-based personalized medical traits, and supporting optimal decisions in complex medical situations, leading to insights that can contribute to efficient care approaches and improved patient outcomes.
Feature selection in Neuroimaging
● Our team research about multi-agent reinforcement learning framework that performs feature selection by identifying the most relevant features in a dataset.
● Multi-agent systems facilitate efficient collaboration and communication among agents, and their cooperative learning dynamics are supported by solid theoretical foundations.
Hyperparameter optimization
● We aim to automate and dynamically optimize the hyperparameters in neural networks using gradient-free methods such as evolutionary algorithms and Bayesian optimization.
● Automatic hyperparameter optimization allows the model to adapt to new conditions in real-world applications.
