Biography: Junshan Zhang is a professor in the ECE Department at University of California Davis. His research interests fall in the general field of information networks and data science, including edge AI, reinforcement learning, continual learning, network optimization and control, game theory, with applications in connected and automated vehicles, 5G and beyond, wireless networks, IoT data privacy/security, and smart grid.
Talk Title:
Towards Theoretic Foundation for World Models
Talk Abstract :
We consider a multi-agent network where agents interact with others in a dynamic environment.
In general, multi-agent reinforcement learning faces formidable technical challenges, due to 1) the curse of dimensionality, 2) the curse of partial observability and multi-agency, and 3) the curse of non-stationarity. To tackle these challenges, we propose a world model based distributed reinforcement learning framework.
Aiming to build a theoretic foundation, we characterize the latent representation error in world models and quantify its impact on the prediction capability.
