AI RESEARCH

Robust Transfer Learning with Side Information

arXiv CS.LG

ArXi:2603.07921v1 Announce Type: cross Robust Marko Decision Processes (MDPs) address environmental shift through distributionally robust optimization (DRO) by finding an optimal worst-case policy within an uncertainty set of transition kernels. However, standard DRO approaches require enlarging the uncertainty set under large shifts, which leads to overly conservative and pessimistic policies.