The purpose of this project is to develop physics informed Machine Learning (ML) methods to accelerate and/or complement state-of-the-art simulation methods for Soft-Matter flows. Following our work of the previous two years, we are considering three basic problems: (A) ML for polymer rheoogy, (B) ML Stokes Flows, and (C) ML for "smart" swimmers. For topic (A), we have extended our method to learn the constitutive relation of entangled polymer melts for generic multi-deformation mode flows in 2D. For topic (B), we have extended our learning method to 3D, and have performed detailed comparisons against Physics Informed Neural Networks, to show the robustness and efficiency of our approach. Finally, for topic (C), we have extended our Reinforcement Learning method to consider load-carrying swimmers in complex flows.