Model-tuning and tracking your agent's long-term performance

As we build and tune our models, we need to test their performance and make sure they are improving with respect to speed and accuracy. In general, a model that performs better as it is fed more data is a model that is fitted well to its training environment. Let's test the performance of our baseline agent against our learning model and observe what happens when we run the model over more iterations.

Comparing your models and statistical performance measures

Let's go back to our randomly-acting baseline agent. We've changed the variable name, count, to epochs to distinguish each training time step from each full game loop cycle the agent completes...