How Many Different Kinds of Rearrangement Algorithms Are There?

How many different a reinforcement learning algarithms is our brain running, you know? So let me answer that question by saying that t d learning, temporal difference learning, is also used to learn representations in the successor representation. There are continuous versions of deep successore representations as well. I personally like focus on the tabular first, and then go towards deep because i'm more interested in basic algorithm, algarithm that you can test on behavior  and then go towards the dequence.