What is the relation between Slow Feature Analysis and the Successor Representation?
This work clarifies theoretical connections between unsupervised learning and reinforcement learning methods, which is incremental for researchers in these fields.
This paper investigates the relationship between Slow Feature Analysis (SFA) and the Successor Representation (SR), showing that in a one-hot encoded Markov decision process, they are formally equivalent in terms of grid-like representations and that SFA columns contain place-like representations distinct from prior models.
Slow feature analysis (SFA) is an unsupervised method for extracting representations from time series data. The successor representation (SR) is a method for representing states in a Markov decision process (MDP) based on transition statistics. While SFA and SR stem from distinct areas of machine learning, they share important properties, both in terms of their mathematics and the types of information they are sensitive to. This work studies their connection along these two axes. In particular, both SFA and SR are explored analytically, and in the setting of a one-hot encoded MDP, a formal equivalence is demonstrated in terms of the grid-like representations that occur as solutions/eigenvectors. Moreover, it is shown that the columns of the matrices involved in SFA contain place-like representations, which are formally distinct from place-cell models that have already been defined using SFA.