A Gentle Lecture Note on Filtrations in Reinforcement Learning
It provides an educational resource for learners in RL, but is incremental as it reiterates existing knowledge without new findings.
The note explains the concept of filtrations in reinforcement learning to clarify their role in formal problem definitions, concluding that they are unnecessary due to the Markovian property allowing decisions based solely on current state.
This note aims to provide a basic intuition on the concept of filtrations as used in the context of reinforcement learning (RL). Filtrations are often used to formally define RL problems, yet their implications might not be eminent for those without a background in measure theory. Essentially, a filtration is a construct that captures partial knowledge up to time $t$, without revealing any future information that has already been simulated, yet not revealed to the decision-maker. We illustrate this with simple examples from the finance domain on both discrete and continuous outcome spaces. Furthermore, we show that the notion of filtration is not needed, as basing decisions solely on the current problem state (which is possible due to the Markovian property) suffices to eliminate future knowledge from the decision-making process.