University of Minnesota Morris

Cooperative multi-agent reinforcement learning with entangled state representations and copula-based action coordination for urban navigation

Abstract Cooperative multi-agent reinforcement learning (MARL) enables autonomous agents to coordinate in complex spatial environments. This study proposes a MARL framework for goal-directed navigation that integrates entangled state embeddings, copula-based joint action transfor...

A Copula-Tensor Neural Network Framework for High-Dimensional Causal Inference

Estimating conditional average treatment effects (CATEs) in high-dimensional causal inference problems remains challenging because complex nonlinear relationships, heterogeneous feature distributions, and dependence among covariates can limit the effectiveness of conventional mac...