PhD Dissertation Proposal by CHEN Changyu | Interactive Generative Models: A Pathway for Improved Simulation and Decision Making

The rapid advancement of generative models has shown significant success in various domains. However, most works of generative models aim to learn the underlying data distribution by a single generative model, while the utilization of generative models to learn the data generation process involving informative interactions is still in its early stages. For example, in a multi-agent system such as transportation system,  different agents exhibit different kinds of behavior. A single generative model can capture the average behavior within such a system but struggles to model the varied behaviors of different agents. In order to model the varied behaviors, one must also model the interactions between agents. Our work investigates this under-explored aspect, forming the concept Interactive Generative Models (IGMs). We delve into how interactions can enhance generative models, leading to the improvement of their capabilities and broadening of their use-cases.

CHEN Changyu is a Ph.D. candidate in Computer Science at the SMU School of Computing and Information Systems, co-supervised by Prof. Pradeep Varakantham and Prof. Arunesh Sinha (Rutgers Business School). His research focuses on generative modeling and its application in reinforcement learning.