# Two-stage Learning Step for Backpropagation in a Relational Autoencoder

Working on gradient descent / backpropagation for a relational autoencoder. I'm not really sure this is needed yet, so I have to build the testing framework for it all. Separately I'm implementing a RL agent that uses Least Squares Policy Iteration to learn. Let X and Y be two sets of training examples of sizes N and M respectively Select $latex x \in X $ and $latex y \in Y $ randomly Feed $latex (x,y)$ forward Step 1 - Train X Hold w and x constant and minimize cost by treating y' as a parameter Calculate error on x side of cost function Backprop error Update W (and b) only on the X side Step 2 - Train Y Hold w and y constant and minimize cost by treating x' as a…