This came up a couple of days ago: <a href="https://news.ycombinator.com/item?id=17637683" rel="nofollow">https://news.ycombinator.com/item?id=17637683</a>
I skimmed through this and have already found a bunch of interesting sections, but there's also a ton of background information on topics related to bandit algorithms.<p>The authors say that this is the first draft of the book submitted to the publisher, so I suppose it's nearly complete?
More details available at the site they put up, <a href="http://banditalgs.com/" rel="nofollow">http://banditalgs.com/</a>
Never heard of bandit algorithms before! Or if I did I didn't recognize it as something different from probability. What have people around here used them for?
It always makes me sad that Thompson Sampling isn't (or at least doesn't appear to be) mentioned alongside things like UCB1. Its theoretically optimal, and relatively easy to grok, and not significantly more difficult to implement.
I really appreciate sharing the book. However, to everyone in charge with naming these files, please don't call it "book.pdf". It makes everyone go to their computer and rename the file after downloading it so that they can find it later. Give it a more intuitive name.<p>Thanks