On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction

We extend adaptive MRI subsampling methods to the more clinically-relevant multi-coil setting.

Back to Basics: Deep Reinforcement Learning in Traffic Signal Control

We revisit basic assumptions in Deep RL for traffic signal control and define an MDP that outperforms current SotA.

Experimental design for MRI by greedy policy search

We use policy gradient methods to learn active acquisition policies for improving MRI reconstruction.