It's interesting just to go through their comments.
I do have a small issues with PDFs like this one, please give me a TOC on the left sidebar for easy navigation.
Has applications in a wide variety of fields : optimal design of clinical trials, public policy decision making.
apparently has some relation to the work abhijit banerjee & esther duflo, the nobel prize winning economist couple have done on design of experiments, to measure impact of developmental interventions
I find MAB's incredibly interesting, and for pretty much the same reason(s) I find the rest of this stuff interesting.
It does look quite clear, well thought and well structured.
The book goes into more details around, well, a lot of things.
The trade-off is the more general algorithms needs many times exponentially more data and compute to come to a similarly good solution.
That's why reinforcement learning has seen so practical few applications relative to supervised learning. There's no free lunch.
That said, as a ML practitioner I would love it if I could just apply a single master algorithm to all problems, but that is likely many years away.
At the same time, fine-tuning sample efficiency increases with scale, so at some point you can possibly one-shot learn state and get rid of exponential searches, solving NP-Hard problems with heuristics. Sounds like a free lunch to me. At least if you can afford a net large enough.