sutton

Apparently Sutton was going to do a second book, but has since retreated to a second edition.

Judging from the slides, this lecture must have been particularly awesome, though the slides from the Sutton lecture are interesting as well.

I read Sutton and Barto on Q-Learning but only 'got' it when I saw it hand-done with matrix math.

For other cases (and the DIYers among us) Thomas Sutton wrote up instructions for setting up dnsmasq[2] on OS X for app development.

It's a 2012 followup by Mike Sutton to the two publications from 2010.

Agree with others that Barto & Sutton is dated, but it's not obsolete.

I guess you can count Yann LeCun, Leon Bottou and Richard Sutton among those.

I chatted with Rich Sutton recently and he said he was writing and update - not sure how far along in the process he is though.

In the words of famed bank robber Willie Sutton: "Go where the money is."

I think he just means "don't be an asshole", in the Bob Sutton sense.

Does that latter fact perhaps reflect the Willie Sutton principle, per Wikipedia: " Sutton is known, albeit apocryphally, for the urban legend that he said that he robbed banks 'because that's where the money is.' " I.e.

Reminds me of Bob Sutton, a Stanford prof and author who writes[1]: "This tendency to look for individual goats – and heroes – isn’t just a problem that permeates the world of sports.

The entire situation reminds me of the infamous American bank robber, Willie Sutton, who supposedly said that he robbed banks because that's where the money is [1,2].

Sutton's law: that's where the money is.

Sutton has just finished talking about how in real life, functions that learning agents wish to estimate will often be non-stationary because life is constantly changing.