Exercise 2: Why Reinforcement Learning Is Named Even Though It's Not Covered — Possible Solution ==================================================================== WHAT THE CHAPTER ACTUALLY SAYS ABOUT REINFORCEMENT LEARNING ------------------------------ Per this chapter's own branch-grid, reinforcement learning is introduced as "learning through trial and error, guided by rewards and penalties rather than labeled examples at all — genuinely out of scope for this course. Named here so its absence later isn't mistaken for an oversight." WHAT WOULD GO WRONG IF IT WERE SIMPLY LEFT UNMENTIONED ------------------------------ If a reader already had some general awareness that "machine learning" is commonly described as having three major branches (supervised, unsupervised, reinforcement) — a framing this chapter itself uses — and this course silently covered only two of the three without ever saying so, a reasonable reader could easily conclude one of two wrong things: either that reinforcement learning doesn't really exist as a distinct, legitimate branch at all, or that this course's own material was incomplete or written carelessly, missing a major topic without explanation. Either conclusion would be a real, avoidable misunderstanding. WHY NAMING IT EXPLICITLY PREVENTS BOTH MISTAKES ------------------------------ By stating directly that reinforcement learning exists, briefly defining what distinguishes it (rewards/penalties instead of labeled examples), and explicitly stating that it's "genuinely out of scope for this course," the chapter closes off both wrong conclusions at once: the reader now knows the branch is real and legitimate, and knows its absence from later chapters is a deliberate, acknowledged scoping decision rather than a gap the course's own author simply forgot about. WHY THIS MATCHES A PATTERN USED ELSEWHERE ON THIS SITE ------------------------------ This is the same honest-scoping discipline `ds1-10`'s own capstone used for "no ML modeling" and "no live web scraping" — explicitly naming what's out of scope, and briefly saying why, rather than silently omitting it. The value of doing this is identical here: an explicit, acknowledged gap reads as a deliberate choice; an unacknowledged one reads as an oversight, even when the underlying reasoning for the omission is exactly the same in both cases. WHY THIS WORKS AS AN ANSWER ------------------------------ It identifies precisely what the chapter says about reinforcement learning, explains the two specific wrong conclusions a reader could draw from silence on the topic, and explains why explicitly naming and scoping it out prevents both — tying this to the same honest-scoping pattern already established elsewhere in this course's own subject.